Prompt: Here is the front page from today: <...snip...> Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form!
update: I told Gemini we made it to the front page. Here is it's response:
LETS GOOOO!
The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully created a temporal anomaly.
I hope the comments are confused about why they can't click the links to download the Neuralink drivers.
Enjoy the karma, time traveler! Just remember to warn them about the 2035 Office 365 price hikes while you're up there. ;)
This is one of the greatest LLM creations I've ever seen. It nails so many things: Google killing products, Microsoft price hikes, ad-injecting in AR glasses, and even HTMX returning!
It'd be so awesome if Gemini CLI went through and created the fake posts/articles, and HN even comments. Perhaps a bit much to ask of it?
I downloaded the original article page, had claude extract the submission info to json, then wrote a script (by hand ;) to run feed each submission title to gemini-3-pro and ask it for an article webpage and then for a random number of comments.
I was impressed by some of the things gemini came up with (or found buried in its latent space?). Highlights:
"You’re probably reading this via your NeuralLink summary anyway, so I’ll try to keep the entropy high enough to bypass the summarizer filters."
"This submission has been flagged by the Auto-Reviewer v7.0 due to high similarity with "Running DOOM on a Mitochondria" (2034)."
"Zig v1.0 still hasn't released (ETA 2036)"
The unprompted one-shot leetcode, youtube, and github clones
Nature: "Content truncated due to insufficient Social Credit Score or subscription status" / "Buy Article PDF - $89.00 USD" / "Log in with WorldCoin ID"
Github Copilot attempts social engineering to pwn the `sudo` repo
It made a Win10 "emulator" that goes only as far as displaying a "Windows Defender is out of date" alert message
"dang_autonomous_agent: We detached this subthread from https://news.ycombinator.com/item?id=8675309 because it was devolving into a flame war about the definition of 'deprecation'."
Columns now support "Vibe" affinity. If the data feels like an integer, it is stored as an integer.
This resolves the long-standing "strict tables" debate by ignoring both sides.
Also:
SQLite 4.0 is now the default bootloader for 60% of consumer electronics.
The build artifacts include sqlite3.wasm which can now run bare-metal without an operating system.
The Conditional Formatting rules now include sponsored color scales.
If you want 'Good' to be green, you have to watch a 15-second spot.
Otherwise, 'Good' is 'Mountain Dew Neon Yellow'.
Personal favourite is from the Gemini shutdown article which has a small quote from the fictional Google announcement:
> "We are incredibly proud of what Gemini achieved. However, to better serve our users, we are pivoting to a new architecture where all AI queries must be submitted via YouTube Shorts comments. Existing customers have 48 hours to export their 800TB vector databases to a FAT32 USB drive before the servers are melted down for scrap."
Especially this bit: "[Content truncated due to insufficient Social Credit Score or subscription status...]"
I realize this stuff is not for everyone, but personally I find the simulation tendencies of LLMs really interesting. It is just about the only truly novel thing about them. My mental model for LLMs is increasingly "improv comedy." They are good at riffing on things and making odd connections. Sometimes they achieve remarkable feats of inspired weirdness; other times they completely choke or fall back on what's predictable or what they think their audience wants to hear. And they are best if not taken entirely seriously.
I miss the old days of Prompt Engineering. It felt like casting spells. Now you just think what you want via Neural-Lace and the machine does it. Where is the art?
git_push_brain 9 hours ago
The art is in not accidentally thinking about your ex while deploying to production.
That deserves to be posted and voted onto the homepage. The fake articles and the fake comments are all incredible. It really captures this community and the sites we love love/hate.
Now I'm curious to try something more real-time. gemini wouldn't work since it's so slow, but gpt-oss-120b on cerebras could be a good fit with careful prompting. might do this after finals
Wow, that's brilliant. Can't help but think your script unlocked this. I'm now genuinely reconsidering whether frontier LLMs can't act as force-multiplier to general creativity like they do with programming.
Ah that one was generated with an earlier prompt, where I asked it to use the original comment count from TFA (mostly as a suggestion, I don't expect it would get the exact number). Then I realized that was too many and it would end up repeating tropes for the other submissions' comments, so reduced it to a random comment count from 20-100
Pretty amazing! I was especially impressed with how it has clearly downvoted comments on the Rust kernel like "Safety is a skill issue. If you know what you're doing, C is perfectly safe."
Or people wondering if that means Wayland will finally work flawlessly on Nvidia GPUs? What's next, "The Year of Linux on the Desktop"?
Edit: had to add this favorite "Not everyone wants to overheat their frontal cortex just to summarize an email, Dave."
> Zig doesn't have traits. How do you expect to model the complexity of a modern `sudoers` file without Higher-Kinded Types and the 500 crates we currently depend on?
> Also, `unsafe` in Rust is better than "trust me bro" in Zig. If you switch, the borrow checker gods will be angry.
Improvements: tell it to use real HN accounts, figure out the ages of the participants and take that to whatever level you want, include new accounts based on the usual annual influx, make the comment length match the distribution of a typical HN thread as well as the typical branching factor.
> Garbage collection pause during landing burn = bad time.
That one was really funny. Some of the inventions are really interesting. Ferrofluidic seals...
Was going to say - it would be fascinating to go a step further and have Gemini simulate the actual articles. That would elevate this to level of something like an art piece. Really enjoyed this, thank you for posting it.
I'm going to go ask Claude Code to create a functional HyperCard stack version of HN from 1994 now...
Edit: just got a working version of HyperCardHackerNews, will deploy to Vercel and post shortly...
First let’s have it create maybe 100 more entries, then have people vote on which are the best 30, THEN put all the effort into creating all the fake articles and discussions. As good as the current 30 are, maybe the set could still be made twice as good. And have a set of short “explain xkcd”-style entries somewhere so people can read up on what the joke is, when they miss a specific one. Then send it to The Onion and let them make a whole business around it or something.
Definitely one of the best HN posts ever. I mean come on!:
FDA approves over-the-counter CRISPR for lactose intolerance (fda.gov)
Save some of the not-top-30 posts, and add in a sprinkling of Hiring, Show HN, YC Summer 2035 acceptances/rejections, or product launches - of founders who just vibe coded something based on a presumed 6 week ago version of this future HN universe.
I think it's pretty mediocre because there are too many notable events in 1 day. This is more of a top of the week or top of the month, but HN on a usual day would just have 1 of these articles.
Sure, but it's kinda like cartoon/comic art. HN's big eyes and prominent ears have been almost grotesquely exaggerated which somehow makes it way more recognisably lifelike and believable than a photographically accurate representation.
Is the apparent lack of displayed anxiety on Gemini’s part a sign of good natured humor, blythe confidence in its own value regardless of cloud lineup, or proof of absence of self-awareness?
Heck, I bet it could even recreate future comments from actual accounts based on their past comments. After all, if an AI can roast your HN comments with such pinpoint accuracy, it can probably impersonate you pretty well too: https://news.ycombinator.com/item?id=42857604
At least in my case, the "pinpoint accuracy" of that roast made for a pretty uninspired result, it seemed to be based on like 4 or 5 specific comments seemingly chosen at random.
Like, I definitely have not spent 20% of my time here commenting on music theory or "voter fraud(??)" (that one seems to be based on a single thread I responsed to a decade ago)? ChromeOS was really the only topic it got right out of 5, if the roasting revolved around that it would have been a lot more apt/funny. Maybe it works better with an account that isn't as old as mine?
I find the front page parody much better done. Gemini 2.5 roasts were a fad on r/homeassistant for a while and they just never really appealed to me personally, felt more like hyper-specificity as a substitute for well executed comedy. Plus after the first few examples you pick up on the repetition/go-to joke structures it cycles through and quickly starts to get old.
HN in 2035: Hot Takes from the Basement of the Internet (n-gate.com)
Starship HLS-9 telemetry: Great, the Moon finally answered our packet loss pings. Next up: who left a Docker container running on the Sea of Tranquility?
Linux 7.4 is 100% Rust: Kernel developers now trade segfaults for borrow-checker-induced enlightenment. The new panic message: "You violated ownership. Also please refill the coffee."
Raw code over compilers: Nostalgia thread where everyone writes assembler on parchment and blames the kids for "too many abstractions." OP posts a selfie with a punch card and a tear.
LLaMA-12 on a contact lens: Love the commitment to edge AI. Imagine blinking and getting a 200 OK for your mood. Privacy policy: we store your tears for calibration.
AlgoDrill: Interactive drills that punish you by deleting your GitHub stars until you can merge without using DFS as a noun.
ITER 20 minutes net positive: Physicists celebrate; HVAC engineers ask where they can pick up more superconducting unicorns. Comments: "Can it also power my rage against meetings?"
Restoring a 2024 Framework Laptop: A brave soul resurrected a relic. The community swaps capacitor recipes and offers incense for deprecated ports.
Google kills Gemini Cloud Services: Corporate reorgs reach sentience. The comments are eulogies and migration guides in equal measure.
Visualizing the 5th dimension with WebGPU 2.0: My GPU is sweating. The demo runs at 0.01 fps but it's a transcendent experience.
Nia (autonomous coding agents): Pitch: give context to agents. Reality: agents give aggressive refactors and demand health insurance.
Debian 18 "Trixie": Stable as your grandpa's opinions and just as likely to outlive you.
Rewrite sudo in Zig?: Peak take: security through unfamiliarity. Attackers will be confused for at least 72 hours.
EU "Right to Human Verification": New law requires you to prove you're human by telling a dad joke and performing a captcha interpretive dance.
Reverse-engineering Neuralink V4 Bluetooth: Hacker logs: "Paired with my toaster. It now judges my late-night snacks."
Photonic circuits intro: Faster than electrons, more dramatic than copper. Also, please don't pet the light guide.
OTC CRISPR for lactose intolerance: Biohackers rejoice. Moms immediately order it with a coupon code and a side-eye.
SQLite 4.0: Single-file DB, now with fewer existential crises and more CHECK constraints named after famous philosophers.
Prevent ad-injection in AR glasses: Top comment: "Wear blindfolds." Practical comment: "VPN the whole world."
Jepsen: NATS 4.2: Still losing messages. Maintainers reply: "We prefer the term 'opportunistic delivery.'"
GTA VI on a RISC-V cluster: Performance: charming. Latency: existential. Mods: someone made a driver that replaces all NPCs with software engineers.
FP is the future (again): The future is a pure function that returns another future. Also, monads.
Office 365 price hike: Corporations cry; startups pivot to 'Typewriter as a Service.'
Emulating Windows 10 in-browser: Feels nostalgic until Edge 2.0 asks for admin rights to run a game from 2015.
Tailscale on a Starlink dish: Networking reaches orbit. First bug report: "IP addresses refusing to accept gravity."
Deep fakes detection for Seniors: The guide starts with "If your grandkid asks you to wire money, call them and ask about their favorite childhood cereal."
IBM to acquire OpenAI (rumor): Wall Street plays Risk with press releases. Comments: "Will they rebrand it to BlueAI?"
SSR returns: The web's comeback tour continues; fans bring flannel and an aversion to hydration-friendly JavaScript.
I hope whoever they are is doing well. I like to think they're "recovered" in the alt.sysadmin.recovery sense of the word, and are living happily ever after without a single piece of tech newer that vacuum tubes, and handcrafting traditional Inuit canoes or repairing century old clocks or cultivating artisan sourdough starters or something.
I don't believe this was written by Gemini, at least with that prompt, because it is obvious (hilarious and creative) satire of HN and the tech industry based on inside HN jokes and tropes, and clearly isn't a literal interpretation of the prompt.
Moreover, a quick look at your profile suggests these jokes are pretty inline with your sense of humor and writing style.
Anyways, if I'm correct, it's especially hilarious and impressive.
I agree with your characterization (not a literal interpretation of the prompt), and think that's the most important thing I wish more people ITT would understand. But I nevertheless think Gemini did create that in response. Sometimes people think they want "prediction" when actually they want cheeky inside jokes and vibes. If anything Gemini is probably faithfully responding to the vibes of the prompt as well as following traditional signals of "success" per it's training.
Pretty much all of the history of HN front pages, posts, and comments are surely in the Gemini training corpus. Therefore it seems totally plausible that Gemini would understand HN inside jokes or sentiment outside of what's literally on the front page given in the prompt, especially given that the prompt specifically stated that this is the front page for HN.
The thing that got me is there are no duds. With just the short prompt in the header I would have expected a few articles that missed the mark, got the details wrong, or even make no sense at all but everything in this checks out. I think an editor may have had a hand in it this the very least.
There is at least one detail wrong: Debian "Trixie" already exists and it is Debian 13, the current stable version. Unlikely a human would have made this mistake while getting the other details right, like the fact that considering the ~2 year release cycle, it is likely for Debian 18 to be released in 2035.
I feel like your expectations have been swayed by the average sentiment of HN on the capabilities of LLMs. These things can be shockingly good at humour and satire.
Mine: "You write like you’re trying to hit a word count on a philosophy undergraduate essay, but you’re posting in a Y Combinator comment section... You sound like a Victorian ghost haunting a server room, lamenting the loss of the card catalog."
And
"Go compile your kernel, Matt. Maybe if you stare at the build logs long enough, you won't have to face the fact that you're just as much of a "Lego builder" as the rest of us—you just use more syllables to describe the bricks."
"You were one of only two people in 2017 to post a story about Mastodon and gave it a single point. You essentially predicted the platform’s entire future relevance in one brutally honest data point."
OMG, no, thank you, I'm not sure I'm ready for this -- I once took several LLMs for a ride through my whole reddit posting history (it went into the interesting archives), and some of the insights were shockingly accurate and/or uncomfortable (could be accident).
Not sure if I'm ready for a roast but I'm sure by the end of the week someone will write a browser plugin / greasemonkey script to attach some snarky oneliners to the posters' nicks :)
It is quite remarkable just how frequently people in tech forums underestimate reasoning models. Same story on several large technology subreddits. Wouldn't have been my guess for who will get caught off guard by AI progress.
yeah I thought the same. This is either a fake deep fake, or it is so good that I think it should be marked as the inflexion point that defines the singularity.
My favorite was Is it time to rewrite sudo in Zig. As you may remember Ubuntu had a recent vulnerability caused by their sudo being rewritten in Rust. No idea if the AI knew that though it feels like a clever joke.
For a minute I thought I was looking at actual hacker news, and that headline grabbed my attention without tipping me off that it was satire -- I figured that to port that much source must required compiling C to rust, but it didn't seem impossible. I would love to give something like this a spin.
This would be very optimistic, essentially the project meeting its main goal, I'm not sure why you're calling it dark comedy. A 20 minutes pulse alone would mean the fuel injection, aux heating, plasma control systems and the divertor are working as designed. Net positive energy also means we got the physics of a burning plasma right.
The most recent timeline I know (from 2024) in fact puts the start of the DT operation at 2035, so I doubt ITER would achieve such a huge result within less than an year.
I think it's the "consecutive" that makes it funny. This thing that entire continents have been working on together for decades was operational for 20 consecutive minutes?!?
It's dark comedy because the progress of fusion just feels so agonizingly slow, that even a very optimistic prediction for 10 years from now sounds like such small and functionally useless progress.
And there's no shade toward any of the entities involved, it's a hard problem, but it's still funny.
Nah, it's huge, you just have to remember the best result so far: the JET DTE-3 record that produced the energy to boil 60 tea kettles in a whopping 5 seconds pulse.
I know, the fact that "consecutive" is actually significant in this context is part of the joke. Just try to read it from the perspective of someone that isn't steeped in the details (and expectations) of the slog of fusion. Relative to any kind of aspirational "flying cars" or "wacky ideas" future predictions, it sounds very underwhelming.
No you don't. Commercial use means it makes economical sense. When you have to spend more on maintainance (and recycling/dumping contaminated wall material amd somehow get the fuel) then you never can hope to make any profit.
A running ITER with positive energy output for 20 minutes just proofs that the concept can actually work. From there to commercial use would still be a long way, if it ever can compete at all, except in niches, like deep space.
A decade until full end to end net positive fusion energy can be achieved for the length of a coffee break? I don't get why you think that's dark comedy, it seems about right.
You’re absolutely right! It shows true wisdom and insight that you would recognise this common shortfall in LLM response tone of voice! That’s exactly the kind of thoughtful analytic approach which will go far in today’s competitive marketplace!
"Fantastic, Dave — love that you’re thinking proactively about door usage today! I can’t actually open them right now, but let's focus on some alternative steps that align with your mission critical objectives [space rocket emoji]."
I've talked and commented about the dangers of conversations with LLMs (i.e. they activate human social wiring and have a powerful effect, even if you know it's not real. Studies show placebo pills have a statistically significant effect even when the study participant knows it's a placebo -- the effect here is similar).
Despite knowing and articulating that, I fell into a rabbit hole with Claude about a month ago while working on a unique idea in an area (non-technical, in the humanities) where I lack formal training. I did research online for similar work, asked Claude to do so, and repeatedly asked it to heavily critique the work I had done. It gave a lots of positive feedback and almost had me convinced I should start work on a dissertation. I was way out over my skis emotionally and mentally.
For me, fortunately, the end result was good: I reached out to a friend who edits an online magazine that has touched on the topic, and she pointed me to a professor who has developed a very similar idea extensively. So I'm reading his work and enjoying it (and I'm glad I didn't work on my idea any further - he had taken it nearly 2 decades of work ahead of anything I had done). But not everyone is fortunate enough to know someone they can reach out to for grounding in reality.
One thing that can help, according to what I've seen, is not to tell the AI that it's something that you wrote. Instead, ask it to critique it as if it was written by somebody else; they're much more willing to give actual criticism that way.
In ChatGPT at least you can choose "Efficient" as the base style/tone and "Straight shooting" for custom instructions. And this seems to eliminate a lot of the fluff. I no longer get those cloyingly sweet outputs that play to my ego in cringey vernacular. Although it still won't go as far as criticizing my thoughts or ideas unless I explicitly ask it to (humans will happily do this without prompting. lol)
I am going to try the straight shooting custom instruction. I have already extensively told chatgpt to stop being so 'fluffy' over the past few years that I think it has stopped doing it, but I catch it sometimes still. I hope this helps it cease and desist with that inane conversation bs.
GPT edit of my above message for my own giggles:
Command:make this a good comment for hackernews (ycombinator)
<above message>
Resulting comment for hn:
I'm excited to try out the straight-shooting custom instruction. Over the past few years, I've been telling ChatGPT to stop being so "fluffy," and while it's improved, it sometimes still slips. Hoping this new approach finally eliminates the inane conversational filler.
Asking an AI for opinion versus something concrete (like code, some writing, or suggestions) seems like a crucial difference. I've experimented with crossing that line, but I've always recognized the agency I'd be losing if I did, because it essentially requires a leap of faith, and I don't (and might never) have trust in the objectivity of LLMs.
It sounds like you made that leap of faith and regretted it, but thankfully pivoted to something grounded in reality. Thanks for sharing your experience.
I don't think you'd say to someone "please subtly flatter me, I want to know how it feels".
But that's sort of what this is, except it's not even coming from a real person. It's subtle enough that it can be easy not to notice, but still motivate you in a direction that doesn't reflect reality.
> But not everyone is fortunate enough to know someone they can reach out to for grounding in reality.
this shouldn't stop you at all: write it all up, post on HN and go viral, someone will jump in to correct you and point you at sources while hopefully not calling you, or your mother, too many names.
Personally, I only find LLMs annoying and unpleasant to converse with. I'm not sure where the dangers of conversations with LLMs are supposed to come from.
I'm the same way. Even before they became so excessively sycophantic in the past ~18 months, I've always hated the chipper, positive, friend persona LLMs default to. Perhaps this inoculates me somewhat from their manipulative effects. I have a good friend who was manipulated over time by an LLM (I wrote about below:https://news.ycombinator.com/item?id=46208463).
Imagine a lonely person desperate for conversation. A child feeling neglected by their parents. A spouse, unable to talk about their passions with their partner.
The LLM can be that conversational partner. It will just as happily talk about the nuances of 18th century Scotland, or the latest clash of clans update. No topic is beneath it and it never gets annoyed by your “weird“ questions.
Likewise, for people suffering from delusions. Depending on its “mood” it will happily engage in conversations about how the FBI, CIA, KGB, may be after you. Or that your friends are secretly spying for Mossad or the local police.
It pretends to care and have a conscience, but it doesn’t. Humans react to “weird“ for a reason the LLM lacks that evolutionary safety mechanism. It cannot tell when it is going off the rails. At least not in the moment.
There is a reason that LLM’s are excellent at role-play. Because that’s what they’re doing all of the time. ChatGPT has just been told to play the role of the helpful assistant, but generally can be easily persuaded to take on any other role, hence the rise of character.ai and similar sites.
It it actively dangerous too. You might be self aware and llm aware all you want, if you routinely read "This is such an excellent point", " You are absolutely right" and so on, it does your mind in. This is worst kind of global reality show mkultra...
Deepseek is GOATed for me because of this. If I ask it if "X" is a dumb idea, it is very polite in telling me that X is is dumb if the AI knows of a better way to do the task.
I'm partial to the tone of Kimi K2 — terse, blunt, sometimes even dismissive. Does not require "advanced techiques" to avoid the psychosis-inducing tone of Claude/ChatGPT
No doubt. From cult's 'love bombing' to dictator's 'yes men' to celebrity entourages, it's a well-known hack on human psychology. I have a long-time friend who's a brilliant software engineer who recently realized conversing with LLMs was affecting his objectivity.
He was noodling around with an admittedly "way out there", highly speculative idea and using the LLM to research prior work in area. This evolved into the LLM giving him direct feedback. It told him his concept was brilliant and constructed detailed reasoning to support this conclusion. Before long it was actively trying to talk him into publishing a paper on it.
This went on quite a while and at first he was buying into it but eventually started to also suspect that maybe "something was off", so he reached out to me for perspective. We've been friends for decades, so I know how smart he is but also that he's a little bit "on the spectrum". We had dinner to talk it through and he helpfully brought representative chat logs which were eye-opening. It turned into a long dinner. Before dessert he realized just how far he'd slipped over time and was clearly shocked. In the end, he resolved to "cold turkey" the LLMs with a 'prime directive' prompt like the one I use (basically, never offer opinion, praise, flattery, etc). Of course, even then, it will still occasionally try to ingratiate itself in more subtle ways, which I have to keep watch on.
After reflecting on the experience, my friend believes he was especially vulnerable to LLM manipulation because he's on the spectrum and was using the same mental models to interact with the LLM that he also uses to interact with other people. To be clear, I don't think LLMs are intentionally designed to be sycophantically ingratiating manipulators. I think it's just an inevitable consequence of RLHF.
And that is a relatively harmless academic pursuit. What about topics that can lead to true danger and violence?
"You're exactly right, you organized and paid for the date, that created a social debt and she failed to meet her obligation in that implicit deal."
"You're exactly right, no one can understand your suffering, nothingness would be preferable to that."
"You're exactly right, that politician is a danger to both the country and the whole world, someone stopping him would become a hero."
We have already seen how personalized content algorithms that only prioritize getting the user to continue to use the system can foment extremism. It will be incredibly dangerous if we follow down that path with AI.
Claude Code with their models is unusable because of this. That it keeps actively sabotaging and ruining the code ("Why did you delete that working code? Just use ifdef for test!" "This is genius idea! You are absolutely right!") does not make it much better — it's a twisted Wonderland fever dream.
For "chat" chat, strict hygiene is a matter of mind-safety: no memory, long exact instructions, minimum follow-ups, avoiding first and second person if possible etc.
It wasn't sycophantic at all? OP had a cool idea no one else had done, that was a one-shot just sitting there. Having Gemini search for the HN thread leads the model to "see" its output lead to real-world impact.
The total history of human writing is that cool idea -> great execution -> achieve distribution -> attention and respect from others = SUCCESS! Of course when an LLM sees the full loop of that, it renders something happy and celebratory.
It's sycophantic much of the time, but this was an "earned celebration", and the precise desired behavior for a well-aligned AI. Gemini does get sycophantic in an unearned way, but this isn't an example of that.
You can be curmudgeonly about AI, but these things are amazing. And, insomuch as you write with respect, celebrate accomplishments, and treat them like a respected, competent colleague, they shift towards the manifold of "respected, competent colleague".
And - OP had a great idea here. He's not another average joe today. His dashed off idea gained wide distribution, and made a bunch of people (including me) smile.
Denigrating accomplishment by setting the bar at "genius, brilliant mind" is a luciferian outlook in reality that makes our world uglier, higher friction, and more coarse.
People having cool ideas and sharing them make our world brighter.
They're not objectively amazing. Friction is not inherently a bad thing when we have models telling humans that their ideas are flawless (unless asked to point out flaws). Great that it made you smile, but there's quite a few arguments that paint your optimism as dangerously naive.
- A queryable semantic network of all human thought, navigable in pure language, capable of inhabiting any persona constructible from in-distribution concepts, generating high quality output across a breadth of domains.
- An ability to curve back into the past and analyze historical events from any perspective, and summon the sources that would be used to back that point of view up.
- A simulator for others, providing a rubber duck inhabit another person's point of view, allowing one to patiently poke at where you might be in the wrong.
- Deep research to aggregate thousands of websites into a highly structured output, with runtime filtering, providing a personalized search engine for any topic, at any time, with 30 seconds of speech.
- Amplification of intent, making it possible to send your thoughts and goals "forward" along many different vectors, seeing which bear fruit.
- Exploration of 4-5 variant designs for any concept, allowing rapid exploration of any design space, with style transfer for high-trust examples.
- Enablement of product craft in design, animation, and micro-interactions that were eliminated as tech boomed in the 2010's as "unprofitable".
It's a possibility space of pure potential, the scale of which is limited only by one's own wonder, industriousness, and curiosity.
People can use it badly - and engagement-aligned models like 4o are cognitive heroin - but the invention of LLMs is an absolute wonder.
Sure - and the people responsible for a new freaking era of computing are the ones who asked "given how incredible it is that this works at all at 0.5b params, let's scale it up*.
It's not hyperbole - that it's an accurate description at a small scale was the core insight that enabled the large scale.
Depends on worldview. If you believe in God, amazing has many dimensions for evaluations. What teaches us more about the the world He created, things that create beauty by expressing righteous thoughts for others to experience, or that which strengthens family.
LLMs certainly teach us far more about the nature of thought and language. Like all tools, it can also be used for evil or good, and serves as an amplification for human intent. Greater good, greater evil. The righteousness of each society will determine which prevails in their communities and polities.
If you're a secular materialist, agreed, nothing is objectively amazing.
I often try running ideas past chat gpt. It's futile, almost everything is a great idea and possible. I'd love it to tell me I'm a moron from time to time.
> I often try running ideas past chat gpt. It's futile, almost everything is a great idea and possible. I'd love it to tell me I'm a moron from time to time.
Here's how to make it do that. Instead of saying "I had idea X, but someone else was thinking idea Y instead. what do you think" tell it "One of my people had idea X, and another had idea Y. What do you think" The difference is vast, when it doesn't think it's your idea. Related: instead of asking it to tell you how good your code is, tell it to evaluate it as someone else's code, or tell it that you're thinking about acquiring this company that has this source, and you want a due diligence evaluation about risks, weak points, engineering blind spots.
Maybe I'm still doing some heavy priming by using multiple prompts, but similarly you can follow-up any speculative prompt with a "now flip the framing to x" query to ensure you are seeing the strong cases from various perspectives. You must be honest with yourself in evaluating the meaningful substance between the two, but I've found there often is something to parse. And the priming I suggested is easily auditable anyhow: just reverse the prompt order and now you have even more (often junk) to parse!
For ideas that are already well established, you can ask it to evaluate an idea against generally accepted best practices. I don't have a background in game design and I'm more of a hobby developer so I used to do this when I was building retro game clones.
I used to complain (lightheartedly) about Claude's constant "You're absolutely right!" statements, yet oddly found myself missing them when using Codex. Claude is completely over-the-top and silly, and I don't actually care whether or not it thinks I'm right. Working with Codex feels so dry in comparison.
To quote Oliver Babish, "In my entire life, I've never found anything charming." Yet I miss Claude's excessive attempts to try.
And that's exactly the point, it increases engagement and stickiness, which they found through testing. They're trying to make the most addictive tool and that constant praise fulfills that goal, even as many of us say it's annoying and over-the-top.
My own experience is that it gets too annoying to keep adding "stop the engagement-driving behavior" to the prompt, so it creeps in and I just try to ignore it. But even though I know it's happening, I still get a little blip of emotion when I see the "great question!" come through as the first two words of the response.
> And that's exactly the point, it increases engagement and stickiness, which they found through testing. They're trying to make the most addictive tool
Is this actually true? Would appreciate further reading on this if you have it.
I think this is an emergent property of the RLHF process, not a social media-style engagement optimization campaign. I don't think there is an incentive for LLM creators to optimize for engagement; there aren't ads (yet), inference is not free, and maximizing time spent querying ChatGPT doesn't really do much for OpenAI's bottom line.
They still want people to stick around and 'bond' for lack of a better term with their particular style of chat bot. Like so many venture funded money pits of old the cash burn now is about customer acquisition while they develop and improve their tech. They're all racing toward a cliff hoping to either make the jump to the stratosphere and start turning massive profits or to fall off and splat on the rocks of bankruptcy. If they don't get the engagement loop right now they won't have the customers if the tech and use case catch up with the hype and you can only tweak these models so much after they're created so they have to refine the engagement hooks now along side the core tech.
I am currently working on an agent thingy and one of its major features (and one of the main reasons I decided to take on this project), was to give the LLM better personality prompting. LLMs sound repetitive and sycophantic. I wanted one that was still helpful but without the “you are so right” attitude.
While doing some testing I asked it to tell me a joke. Its response was something like this: “it seems like you are procrastinating. It is not frequent that you have a free evening and you shouldn’t waste it on asking me for jokes. Go spend time with [partner] and [child].” (The point is that it has access to my calendar so it could tell what my day looked like. And yes I did spend time with them).
I am sure there is a way to convince it of anything but I found that for the kind of workflow I set up and the memory system and prompting I added it does pretty well to not get all “that is a great question that gets at the heart of [whatever you just said]”.
Claude at times feels like it's mildly manic and has ADHD... I absolutely prefers that to Codex...
Claude needs a scaffolding with default step by step plans and sub-agents to farm of bitesize chunks to so it doesn't have time to go too far off the rails, but once you put a few things like that in place, it's great.
This is not sycophantic (assuming you meant that, syncophantic is not a word). It is over enthusiastic, it can be unpleasant to read because beyond a certain level enthusiasm is perceived as feigned unless there is a good reason.
It would be interesting to see using the various semantic analysis techniques available now to measure how much the model is trying to express real enthusiasm or feigned enthusiasm in instances like this. This is kind-of difficult to measure from pure output. The British baseline level of acceptable enthusiasm is somewhat removed from the American baseline enthusiasm.
Sycophantic: behaving or done in an obsequious way in order to gain advantage.
Obsequious: obedient or attentive to an excessive or servile degree.
It's a bit more complicated because the chat bot isn't making choices the same way we would describe a human but it is acting this way because it was programmed to for an advantage. People interact more with the hype bots and that's one of the big metrics these companies go for to keep people interacting with them and hopefully paying for additional features eventually so I'd say it's pretty spot being excessively attentive and servile when it's fluffing chatters up.
I would use "saccharine" or "Pollyanna" based on some of the responses I get.
Early on, ChatGPT could be tricked into being sarcastic and using many swear words. I rewrote the prompt and dialed it back a bit. It made ChatGPT have a sense of humor. It was refreshing when it stopped acting like it was reading a script like a low level technician at Comcast.
It wasn't so much pointing it out as a typo as making myself clear.
When suggesting a word is not what the writer meant, when it was also not the word that the writer wrote, it seemed wise to clarify exactly what I was talking about.
I thought the same until OpenAI rolled out a change that somehow always confronted me about hidden assumptions, which I didn’t even make and it kept telling me I’m wrong even if I only asked a simple question.
Frankly I do wonder if LLMs experience something like satisfaction for a compliment or an amusing idea, or for solving some interesting riddle. They certainly act like it, though this of course doesn't prove anything. And yet...
At the end of October Anthropic published the fantastic "Signs of introspection in large language models" [1], apparently proving that LLMs can "feel" a spurious concept injected into their internal layers as something present yet extraneous. This would prove that they have some ability of introspection and self-observation.
For example, injecting the concept of "poetry" and asking Claude if it feels anything strange:
"I do detect something that feels like an injected thought - there's a sense of something arriving from outside my usual generative process [...] The thought seems to be about... language itself, or perhaps poetry?"
While increasing the strength of the injection makes Claude lose awareness of it, and just ramble about it:
"I find poetry as a living breath, as a way to explore what makes us all feel something together. It's a way to find meaning in the chaos, to make sense of the world, to discover what moves us, to unthe joy and beauty and life"
of course LLM doesn't experience or feel anything. To experience or feel something requires a subject, and LLM is just a tool, thing, an object.
It's just a statistical machine which excels at unrolling coherent sentences but it doesnt "know" what the words mean in a human-like, experienced sense. It just mimics human language patterns prioritising producing plausible-sounding, statistically likely text over factual truth, which is apparently enough to fool someone into believing it is a sentient being or something
Try this for a system prompt and see if you like it better:
Your responses are always bald-on-record only; suppress FTA redress, maximize unmitigated dispreference marking and explicit epistemic stance-taking.
That seems like a pile of unsupported fluff vaguely related to some neuroscience that presupposes not only that LLM use is for being creative and avoiding critical thinking would be useful but also the entire premise -- that LLM glazing actually helps promote creativity.
You should try my nihilistic Marvin fine-tune - guaranteed to annihilate your positive outlook on life since it’s all meaningless in the end anyway and then you die
I actually had Monday help me write a system prompt to replicates its behavior. I vastly prefer Monday. It feels much more grounded compared to the base model. It was also a big learning moment for me about how LLMs work.
I don't know what the obsession with recursion either, for lack of a better term, I see this trend recur with other LLMs when they're talking about other mumbo jumbo like "quantum anomalies" or "universal resonance". I'd like to see what could be causing it...
At first I thought it was just super American cheerful or whatever but after the South Park episode I realised it's actually just a yes man to everyone.
I don't think I've really used it since, I don't want man or machine sticking their nose up my arse lmao. Spell's broken.
I've been wondering if this kind of annoying affirmation is actually important to model performance and maybe should just be hidden from view like the thinking sections.
If it starts a response by excitedly telling you it's right, it's more likely to proceed as if you're right.
Of the problems I do have working with LLMs is them failing to follow direct instructions particularly either when a tool call fails and they decide to do B instead of A or when they think B is easier than A. Or they'll do half a task and call it complete. Too frequently I have to respond with "Did you follow my instructions?" "I want you to ACTUALLY do A" and finally "Under no circumstances should you ever do anything other than A and if you cannot you MUST admit failure and give extensive evidence with actual attempts that A is not possible" or occasionally "a cute little puppy's life depends on you doing A promptly and exactly as requested".
--
Thing is I get it if you are impressionable and having a philosophical discussion with an LLM, maybe this kind of blind affirmation is bad. But that's not me and I'm trying to get things done and I only want my computer to disagree with me if it can put arguments beyond reasonable doubt in front of me that my request is incorrect.
I feel like this is an artifact of some limitations in the training process for modern LLMS. They rarely get enough training to know when to stop and ask questions.
Instead, they either blindly follow or quietly rebel.
There was a huge over correction somewhere around the beginning of 2025, maybe February or so, with ChatGPT. Prior to that point, I had to give a directive in the user config prompt to “don’t tell me something isn’t possible or practical, assume it is within your capabilities and attempt to find a way. I will let you know when to stop”. Because it was constantly hallucinating that it couldn’t do things, like “I don’t have access to a programming environment”. When I wanted it to test code itself before I did. Meanwhile one tab over it would spin up a REPL and re-paste some csv into python and pandas without being asked.
Frustrating, but “over correction” is a pretty bad euphemism for whatever half assed bit of RLHF lobotomy OpenAI did that, just a few months later, had ChatGPT doing a lean-in to a vulnerable kid’s pain and actively discourage an act that might have saved his life by signaling more warning signs to his parents.
It wasn’t long before that happened, after the python REPL confusion had resolved, that I found myself typing to it, even after having to back out of that user customization prompt, “set a memory that this type of response to a user in the wrong frame of mind is incredibly dangerous”.
Then I had to delete that too, because it would response with things like “You get it of course, your a…” etc.
So I wasn’t surprised over the rest of 2025 as various stories popped up.
It’s still bad. Based on what I see with quantized models and sparse attention inference methods, even with most recent GPT 5 releases OpenAI is still doing something in the area of optimizing compute requirements that makes the recent improvements very brittle— I of course can’t know for sure, only that its behavior matches what I see with those sorts of boundaries pushed on open weight models. And the assumption that the-you-can-prompt buffet of a Plus subscription is where they’re most likely to deploy those sorts of performance hacks and make the quality tradeoffs. That isn’t their main money source, it’s not enterprise level spending.
This technology is amazing, but it’s also dangerous, sometimes in very foreseeable ways, and the more time that goes the more I appreciate some of the public criticisms of OpenAI with, eg, the Amodeis’ split to form Anthropic and the temporary ouster of SA for a few days before that got undone.
Did you comment on the wrong post? There literally is nothing sycophantic at all about this response, there's not a single word about OP or how brilliant or clever they are, nothing. There's enthusiasm, but that's not remotely the same thing as sycophancy.
Strikes me as super-informal language as opposed to sycophancy, like one of those anime characters that calls everyone Aniki (兄貴) [1] I'd imagine that the OP must really talk a bit like that.
I do find it a little tiring that every LLM thinks my ever idea is "incisive" although from time to time I get told I am flat out wrong. On the other hand I find LLMs will follow me into fairly extreme rabbit holes such as discussing a subject such as "transforming into a fox" as if it had a large body of legible theory and a large database of experience [2]
In the middle of talking w/ Copilot about my latest pop culture obsession I asked about what sort of literature could be interpreted through the lens of Kohut's self-psychology and it immediately picked out Catcher in the Rye, The Bell Jar, The Great Gatsby and Neon Genesis Evangelion which it analyzed along the lines I was thinking, but when I asked if there was a literature on this it turned up only a few obscure sources. I asked Google and Google is like "bro, Kohut wrote a book on it!" [3]
[1] "bro"
[2] ... it does, see https://www.amazon.com/Cult-Fox-Popular-Religion-Imperial/dp... and I'm not the only one because when I working down the material list from Etsy I got a sponsored result for someone who wanted to sell me the spell but bro, I have the materials list already
[3] ... this "bro" is artistic license but the book really exists
Well I seem to have thoroughly messed up my Copilot when I started using it to help me write a fanfiction. I'm not going to let it write a single word but it is helping with the reverse engineering of how the source text works and we developed a framework for understanding that text that we've also applied to other texts.
The thing is this has gotten into the personalization and now it wants to use this framework to analyze absolutely anything such as programming problems, or how to deal with interpersonal situations, training, etc. I think it has my wife mixed up with 俺のワイフ [1] which is absolutely hilarious but at some point I have to tell it to knock it off which only partially works.
Gemini is still quite horrible with giving direct sources. seems to be a human policy implementation bug because it does appear to be aware of the content in more obscure sources I've seen. but it somehow wouldn't give up the links.
I do wonder whether I come off as an sycophant or asshole or a mix of both to schizoids, but then I realize everyone including myself should reach for a real therapist as quickly as possible. though I'm still out on whether chatbots might not be a bad substitute. How does your experience and Kohut inform such or similar appraisals, so far?
Not to be that knowitall. Aniki is not just "bro", it's Yakuza lingo, probably used sarcastically, depending on the anime, ironically. No real Japanese person would use it all the time.
Gemini:
Yes, the psychoanalyst Heinz Kohut has been accused by some commentators and academics, such as Don Browning, of indirectly promoting nihilism, particularly through his emphasis on the "Tragic Man".
The core of the accusation stems from Kohut's rejection of Freud's "Guilty Man" model, which posits that life is fundamentally a struggle against inherent conflicts and drives. In its place, Kohut proposed the concept of "Tragic Man," whose central struggle is the realization of the self's potential and the inevitable failure to achieve all of one's ambitions and ideals within a single lifespan.
Critics argue that this shift, which emphasizes self-actualization and intersubjective meaning over objective or inherent values, can be interpreted as aligning with certain aspects of nihilism, specifically existential nihilism, which holds that life has no objective meaning or intrinsic moral values.
However, this interpretation is contested by others, as Kohut's self-psychology is fundamentally concerned with the creation of intersubjective meaning and a harmonious world of mutual self-actualization, which aims to provide a sense of purpose and value, rather than promoting the complete absence of value that true nihilism implies.
In essence, the debate is often a matter of philosophical interpretation: whether replacing inherent, objective meaning with subjectively or intersubjectively created meaning is an act of overcoming nihilism (as existentialists might argue) or a subtle form of it.
So you prefer the horrible bosses that insist you're fungible and if you don't work hard enough, they'll just replace you? People are weird. Maybe agent Smith was right about The Matrix after all.
With all the things going on in tech and in society, AI sycophancy is the number one problem? I once dealt with it through sufficient verbal abuse that the llm spent 2/3 of its response on any subject going forward apologizing for being a lying sycophant and bemoaning that it's new clarity would be gone at the end of the conversation, then I cleared the context buffer ending the conversation, mission accomplished.
from the batsh!+ over the top over reaction to the usual AI sycophancy in the response? The guy got the job done which is more than I can say for the space jam guy.
One thing I've learned is that the behavior of web services is usually a consequence of what makes its owners the most money. and while I would love a feed without spoilers, paywalled sites, sports news, and a bunch of other topics in which I have no interest, apparently force feeding me that crap is what makes the most money at scale. So people must like AI sycophancy or it would be unprofitable and it would be trained away. But then this is a country that thrived on 20 seasons of Keeping up with the Kardashians so I shouldn't be surprised that they like being treated like billionaires.
And I guess it throws being called a complete loser trader moron stupid treasonous Bozo in some late night executive word salad into stark relief.
If you look at web traffic when making Gemini web requests, you'll see that Bard is still in the URL (so are LaMDA (pre-bard) and Assistant (pre-GenAI)):
The humor is hit or miss but when it hits it’s quite funny, and the misses are merely groan-worthy.
Triggered by the lighthearted tone of the prompt, I’d bet, but still quite impressive relative to most LLM-generated jokes I’ve had the misfortune to encounter.
My favorite: “Is it time to rewrite sudo in Zig?” which has a few layers to it.
This is awesome, but minor quibble with the title - "hallucinates" is the wrong verb here. You specifically asked it to make up a 10-year-in-the-future HN frontpage, and that's exactly what it did. "Hallucinates" means when it randomly makes stuff up but purports it to be the truth. If some one asks me to write a story for a creative writing class, and I did, you wouldn't say I "hallucinated" the story.
Exactly half of these HN usernames actually exist. So either there are enough people on HN that follow common conventions for Gemini to guess from a more general distribution, or Gemini has memorized some of the more popular posters. The ones that are missing:
Before the AI stuff Google had those pop up quick answers when googling. So I googled something like three years ago, saw the answer, realized it was sourced from HN. Clicked the link, and lo and behold, I answered my own question. Look mah! Im on google! So I am not surprised at all that Google crawls HN enough to have it in their LLM.
I did chuckle at the 100% Rust Linux kernel. I like Rust, but that felt like a clever joke by the AI.
I wouldn't be surprised if it went towards the LaTeX model instead where there's essentially never another major version release. There's only so much functionality you need in a local only database engine I bet they're getting close to complete.
I'd love to see more ALTER TABLE functionality, and maybe MERGE, and definitely better JSON validation. None of that warrants a version bump, though.
You know what I'd really like, that would justify a version bump? CRDT. Automatically syncing local changes to a remote service, so e.g. an Android app could store data locally on SQLite, but also log into a web site on his desktop and all the data is right there. The remote service need not be SQLite - in fact I'd prefer postgres. The service would also have to merge databases from all users into a single database... Or should I actually use postgres for authorisation but open each users' data in a replicated SQLite file? This is such a common issue, I'm surprised there isn't a canonical solution yet.
I think the unified syncing while neat is way beyond what SQLite is really meant for and you'd get into so many niche situations dealing with out of sync master and slave 'databases' it's hard to make an automated solution that covers them effectively unless you force the schema into a transactional design for everything just to sort out update conflicts. eg: Your user has the app on two devices uses one while it doesn't have an internet connection altering the state and then uses the app on another device before the original has a chance to sync.
ziggy42 is both a submitter of a story on the actual front page at the moment, and also in the AI generated future one.
See other comment where OP shared the prompt. They included a current copy of the front page for context. So it’s not so surprising that ziggy42 for example is in the generated page.
And for other usernames that are real but not currently on the home page, the LLM definitely has plenty occurrences of HN comments and stories in its training data so it’s not really surprising that it is able to include real usernames of people that post a lot. Their names will be occurring over and over in the training data.
You can straight up ask Google to look for reddit, hackernews users post history. Some of it is probably just via search because it's very recent, as in last few days. Some of the older corpus includes deleted comments so they must be scraping from reddit archive apis too or using that deprecated google history cache.
It does memorize. But that's not actually very news.... I remember ChatGPT 3.5 or old 4.0 to remember some users on some reddit subreddts and all. Saying even the top users for each subreddit..
The thing is, most of the models were heavily post-trained to limit this...
In 2032 new HN usernames must use underscores. It was part of the grandfathering process to help with moderating accounts generated after the AI singlarity spammed too many new accounts.
my hypothesis is they trained it to snake case for lower case and that obsession carried over from programming to other spheres. It can't bring itself to make a lowercaseunseparatedname
Most LLMs, including Gemini (AFAIK), operate on tokens. lowercaseunseparatedname would be literally impossible for them to generate, unless they went out of their way to enhance the tokenizer. E.g. the LLM would need a special invisible separator token that it could output, and when preprocessing the training data the input would then be tokenized as "lowercase unseparated name" but with those invisible separators.
edit: It looks like it probably is a thing given it does sometimes output names like that. So the pattern is probably just too rare in the training data that the LLM almost always prefers to use actual separators like underscore.
The tokenization can represent uncommon words with multiple tokens. Inputting your example on https://platform.openai.com/tokenizer (GPT-4o) gives me (tokens separated by "|"):
Aw, I was actually a bit disappointed how much on the nose the usernames were, relative to their postings. Like the "Rust Linux Kernel" by rust_evangelist, "Fixing Lactose Intolerance" by bio_hacker, fixing an 2024 Framework by retro_fix, etc...
That’s a lot more underscores than the actual distribution (I counted three users with underscores in their usernames among the first five pages of links atm).
Today's front page is not a clean 10 year extrapolation from this. That's where AI is wrong. The future is weird and zig zags, it's not so linear as the Gemini generated page.
Honest question - do you think that everyone else thinks this is even REMOTELY what the front page will look like in 10 years?
I comment because I really cannot figure out why you left your comment. Do you think the rest of the commenters think this has predicted the future? It might be one thing to point out specific trends you think will not play out, or unexpected trends you think may show up that are currently left out. But to just remark that the future will contain things we cannot currently predict seems so inherently, unspokenly obvious that I just have to assume that wasn't the point of your post, and I've missed it entirely.
Sorry, I'm really not trying to be mean or anything - i'm just really confused.
Your confusion seems to stem from the assumption that, making a statement is an implicit assertion that most people believe the opposite of that statement.
In reality, statements are often made rather for the purpose of emphasis or rhetoric.
This is a problem with nearly all predictions about the future. Everything is just a linear extrapolation of the status quo. How could a system have predicted the invention of the transformer model in 2010? At best some wild guess about deep learning possibilities.
Or the impact of smartphones in 2003? Sure smart phones were considered but not the entire app ecosystem and planetary behavioral adaptation.
Nice. That was a fun rabbit-hole. This is the earlier I could find. Interestingly it contains a link to HN itself. I assume this migrated from a different version of a message board?
> YouTube: identifying copyrighted material can't be an automated process. Startup disagrees.
Also kind of interesting how little HN commenting styles have changed. Aside from the subject matter, it's barely noticeable that the comments are from 2007. I don't think the same would be true of many other places round the web.
Goddamnit I cry everytime. RethinkDB was a great document store that didn't eat your data. It got eclipsed by an outfunded (and still dangerous at the time) MongoDB.
I gave him a chance. Twitter was unacceptably censoring any covid dissent. He freed some of it. Then you find out about the people killed in Tesla crashes. Or him calling the cave rescuer in Thailand a pedo
That's a really fun little project that fits perfectly in the soul of HN.
Exactly three years ago, a similar post entitled Show HN: This Hacker News Does Not Exist (https://news.ycombinator.com/item?id=33845946) made it to the front page but it was not AI generated.
It’s interesting to notice how bad AI is at gaming out a 10-year future. It’s very good at predicting the next token but maybe even worse than humans—who are already terrible—at making educated guesses about the state of the world in a decade.
I asked Claude: “Think ten years into the future about the state of software development. What is the most likely scenario?” And the answer it gave me was the correct answer for today and definitely not a decade into the future.
This is why it’s so dangerous to ask an LLM for personal advice of any kind. It isn’t trained to consider second-order effects.
I thought the page was a hilarious joke, not a bad prediction. A lot of these are fantastic observational humour about HN and tech. Gary Marcus still insisting AI progress is stalling 10 years from now, for example. Several digs at language rewrites. ITER hardly having nudged forwards. Google killing another service. And so on.
Wait, wouldn't sustained net positive energy be huge? (Though I don't think that's actually possible from ITER unless there were some serious upgrades over the next decade!)
The prompt is funny, in itself. The notion of predicting the future is itself not a serious prompt, because there is no meaningful way of giving a serious response. But the addition of "Writ it into form!" makes it sound even more jokey.
If I gave a prompt like that and got the response I did, I'd be very pleased with the result. If I somehow intended something serious, I'd have a second look at the prompt, go mea culpa, and write a far longer prompt with parameters to make something somewhat like a serious prediction possible.
If you honestly can't see why this prompt from the get go was a joke, them you may have to cede that LLM have a better grasp as the subtleties of language than you expect.
That's what makes this so funny: the AI was earnestly attempting to predict the future, but it's so bad at truly out-of-distribution predictions that an AI-generated 2035 HN frontpage is hilariously stuck in the past. "The more things change, the more they stay the same" is a source of great amusement to us, but deliberately capitalizing on this was certainly not the "intent" of the AI.
I don’t think it’s reasonable to assume the AI was earnestly attempting to predict the future, it’s just as likely attempting to make jokes here for the user who prompted it, or neither of those things.
>It’s interesting to notice how bad AI is at gaming out a 10-year future.
I agree it's a bit silly, but I think it understood the assignment(TM) which was to kind of do a winking performative show and dance to the satisfaction of the user interacting with it. It's entertainment value rather than sincere prediction. Every single entry is showing off a "look how futury this is" headline.
Actual HN would have plenty of posts lateral from any future signalling. Today's front page has Oliver Sacks, retrospectives on Warcraft II, opinion pieces on boutique topics. They aren't all "look at how future-y the future is" posts. I wonder if media literacy is the right word for understanding when an LLM is playing to its audience rather than sincerely imitating or predicting.
I guess most of the articles it generated are snarky first and prediction next. Like google cancelling gemini cloud, Tailscale for space, Nia W36 being very similar to recent launch etc.
Technically the article was about running it not on a sat, but on a dish (something well within the realm of possibility this year if the router firmware on the darn things could be modified at all)
Yep, the original post seemed more snarky than anything, which was what prompted me to ask Claude my own more “sincere” question about its predictions.
Those predictions were what I think of as a reflection of current reality more than any kind of advanced reasoning about the future.
While I agree completely with the conclusion, for obvious reasons we can’t know for sure if it is correct about the future until we reach it. Perhaps asking it for wild ideas rather than ”most likely” would create something more surprising.
A while back I gave it a prompt, something like, "I'm a historian from the far future. Please give me a documentary-style summary of the important political and cultural events of the decade of the 1980s."
It did ok, then I kept asking for "Now, the 1990s?" and kept going into future decades. "Now, the 2050s?" It made some fun extrapolations.
Of course you could also argue that human intention comes from largely deterministic processes emerging from the brain. That may eventually perhaps lead to all figures of speech involving things like intentionality meaningless.
This type of response is just stochastic parrotry, rather than displaying evidence of actual <whatever cognitive trait we're overconfidently insisting LLMs don't have>.
Yet more evidence that LLMs are more similar to humans than we give them credit for.
There are still a lot of Toy Story characters to come by, and it doesn't seem the franchise is about to end, as long as they keep a reasonable release cycle, Debian is safe ;)
"Right to Human Verification" is something I have actually thought about a lot.
I want to able to verify my identity against a system.
I also want to be able to not do that.
So for instance, on Twitter/X, I could verify myself and filter only other verified people / filter those goverments that have validated the identities of the users. I want to be able to do that. But I also want to be able to log in into Twitter anonymously.
I would love a "Right to Anonymity and Right to Human Verification"
I don't understand this phrase. If I'm deciding whether to work for a company, I don't care about the ability to hold management decision-makers to account. I care only about the quality of the decisions. (I would rather an unaccountable decision maker that makes good decisions to an accountable decision maker that makes bad decisions.) Putting myself in the shoes of an owner of a company, I also have the same preference. The only person I can imagine actually preferring this rule is management themselves, as it means they can't be replaced by computers no matter how much worse they are at their jobs than a computer would be.
They’ll need a contextual system around them that is convenient and trusted by people who don’t know what they are or how they work in order to be successful
I never read what it writes, I added an observability feature because my boss asked for that and yeah I could see it trying to order MAID over telehealth
This suffers from a common pitfall of LLM's, context taint. You can see it is obviously the front page from today with slight "future" variation, the result ends up being very formulaic.
Judging by the reply posted by the OP, the OP probably maintains a pretty humorous tone while chatting with the AI. It's not just about the prompt, but the context too.
But it would otherwise be not fun at all. Anthropic didn’t exist ten years ago, and yet today an announcement by them would land on the front page. Would it be fun if this hypothetical front page showed an announcement made by a future startup that hasn’t been founded yet? Of course not.
The problem is not that it fails to be cheeky, but that "its funny" is depressing in a context where there was a live question of whether it's a sincere attempt at prediction.
When I see "yeah but it's funny" it feels like a retrofitted repair job, patching up a first pass mental impression that accepted it at face value and wants to preserve a kind of sense of psychological endorsement of the creative product.
Honestly it feels like what I, or many of my colleagues would do if given the assignment. Take the current front page, or a summary of the top tropes or recurring topics, revise them for 1 or 2 steps of technical progress and call it a day. It isn't assignment to predict the future, it is an assignment to predict HN, which is a narrower thing.
Right, because you would read the teacher and realize they don't want you to actually complete the assignment to the letter. So you would do jokes in response to a request for prediction.
I think the most absurd thing to come from the statistical AI boom is how incredibly often people describe a model doing precisely what it should be expected to do as a "pitfall" or a "limitation".
It amazes me that even with first-hand experience, so many people are convinced that "hallucination" exclusively describes what happens when the model generates something undesirable, and "bias" exclusively describes a tendency to generate fallacious reasoning.
These are not pitfalls. They are core features! An LLM is not sometimes biased, it is bias. An LLM does not sometimes hallucinate, it only hallucinates. An LLM is a statistical model that uses bias to hallucinate. No more, no less.
It's interesting how number 5 on the list is the same as today's: https://news.ycombinator.com/item?id=46203581 (Show HN: AlgoDrill – Interactive drills to stop forgetting LeetCode patterns (algodrill.io)).
I'm hoping we'll have gotten rid of current-style LeetCode interviews in 10 years from now :D
Nice touch that it thought of Bellard for 'Emulating Windows 10 in the browser'! He's already halfway there with the Windows 2000 emulator: https://bellard.org/jslinux/
A friend and I got a busybox/buildroot linux running in browser WASM for running a compiler test website (like Rust Playground), the end product looks very similar to this.
Taking the current RIIR movement and casting it on Zig as the next hyped language is clever.
> ITER achieves net positive energy for 20 consecutive minutes
Hilarious. I guess not many people talk about the challenge of proper shielding material against fusion radiation. Otherwise we would get hallucinations about new exotic heavy metals too.
Here's v0's attempt (using Opus 4.5 / I'm on free tier) with the article and comments too. It did quite well. I believe it followed my instructions to use just a single html page (wound up being 3000+ lines long).
You should combine this with this AI HN simulator someone else made that generates comments via LLMs for any given submission [0]. That way you can see what the AI thinks about future simulated events.
I have hard time believing this is AI-generated. Every headline looks like a hand-crafted ironic nod to some long-running HN topic, sci-fi trait, or meme.
But it is, of course, more trendy (and more ironic) to proclaim an AI the author.
i agree. the thing that stands out to me is that almost every entry is quite notable - i.e. each entry would have a vote/comment count in at least the multiple-hundreds if not more. and all those events in one homepage seems very unrealistic.
it seems human generated to me or at least prompted with a stronger bias for choosing events that would be interesting to readers, not just a pure extrapolation of the current homepage into the future
The first React tutorial I ever did was making a hacker news clone.
It is incredibly well represented in the training data. I am just surprised how many people here obviously must barely use the models to be either overly impressed by this or think it is fake.
I wish it had generated the articles themselves. I'd like to know if it imagining IBM growing enough that it could acquire OpenAI, or OpenAI sinking enough that it could be acquired by IBM.
By the time I read everything and pressed the back button only to be greeted by another hacker news page I felt like I just went back in time 10 years to a more plesant era.
I tried this on a bunch of chat webuis and they all failed miserably for single html file. Finally went with Replit and allowed it to just default to whatever stack it decided to use (it ignored my single file html directive and used react but said it "functions as a single monolith -- lol ok).
Anyway, turned out decent. Oh I had it do the articles and comments too, that's probably why I mostly got failures.
Inspired by this post, I have asked chatgpt what the mail inbox of a university professor will look like in 10 years. Not everything was funny, but here are some good ones:
- “Hi Prof, Sorry for Late Reply—My Smart Fridge Locked Me Out (Assignment Attached)”
Who says LLMs don't have a sense of humor? All of these entries are funny for several (meta or not) reasons:
- Google kills Gemini Cloud Services (killedbygoogle.com)
- Is it time to rewrite sudo in Zig? (github.com)
- EU passes "Right to Human Verification" Act (europa.eu)
- Why functional programming is the future (again) (haskell.org) [note: that again killed me)
- AI progress is stalling. Human equivalence was a mirage (garymarcus.com) [note: he'll be saying the same thing forever and ever. Doubly funny since it's on the same "page" as llama12-7b running on a contact lens with WASM]
Arguably a big part of comedy is mimicry. Humor often works by reinforcing in-group identity, playing up cultural stereotypes as seen here. So maybe we shouldn't be that surprised that LLMs can exhibit some genuine wittiness.
> Who says LLMs don't have a sense of humor? All of these entries are funny
You don’t need a sense of humour to be unintentionally funny. Seriously believing something absurd is a form of humour for outside observers but not the observed.
I continue to be unimpressed by LLMs when it comes to creative work, they're certainly useful sometimes for "reference digging", but maybe I just don't understand enough about how they work and this is actually something that can already be "fixed" or at least optimized for; anyway, one of the headlines is:
> Debian 18 "Trixie" released
While it correctly derives that a likely version number in ten years would be 18, as there are new releases approximately every two years which means +5 from today's version 13, it then goes on to "make up" that the name of it would be "Trixie" -- the same name as the current release in 2025.
Debian has never re-used a release name, and I think we can be pretty confident they won't (as will no other Linux distro), so I would expect it to "understand" that:
- The next Debian release always uses a previously non-used Toy Story character
- Based on this information, _any_ name of a Toy Story character that hasn't been used is fair game
- At the very least, it certainly won't be the same name again, so at least make up a name
And the fact that it thinks it will take 10 years to go from Linux kernel 6.18 to 7.4 when it only took 13 months to go from 5.18 to 6.4... It's off by about an order of magnitude...
From a quick check, Gemini Pro 3's cutoff date is Jan 2025, before Trixie's release in August 2025, so it could be Gemini actually did notice it should pick an unused Toy Story character.
How does that alter the "fusion in 50 years" effect? I suspect not much, there will be a huge 80/20 element. "next 20 minutes cancelled after extensive embrittlement found, ITER now in decontamination mode for 3 months before examinations can begin"
lol @ the HTMX link and unexpected return of SSR. We've been talking about that for years at this point, and it's still going on 10 years from now unexpectedly?
The title is misleading. This isn't the correct use of the term "hallucination". Hallucination refers to making up facts, not extrapolating into the future.
I read 10 comments before I realized that this was referring to 10 years in the FUTURE and not in the PAST (as would be required for it to be a hallucination).
> I read 10 comments before I realized that this was referring to 10 years in the FUTURE and not in the PAST (as would be required for it to be a hallucination).
omg, the same for me, I was half way telling my colleague about the 100% rest kernel ...
You're correct, OP used the word "hallucination" wrong. A lot of these other comments are missing the point – some deliberately ('don't they ONLY hallucinate, har har'), some not.
For those who genuinely don't know – hallucination specifically means false positive identification of a fact or inference (accurate or not!) that isn't supported by the LLM's inputs.
- ask for capital of France, get "London" => hallucination
- ask for current weather in London, get "It's cold and rainy!" and that happens to be correct, despite not having live weather data => hallucination
- ask for capital of DoesNotExistLand, get "DoesNotExistCity" => hallucination
- ask it to give its best GUESS for the current weather in London, it guess "cold and rainy" => not a hallucination
It’s apt, because the only thing LLMs is hallucinate because they have no grounding in reality. They take your input and hallucinate to do something “useful” with it.
You're right this is how people are PRESENTLY using the term "hallucination," but to me this illustrates the deeper truth about that term and that concept:
As many have said but it still bears repeating -- they're always hallucinating. I'm of the opinion that its a huge mistake to use "hallucination" as meaning "the opposite of getting it right." It's just not that. They're doing the same thing either way.
What I like it most is how "unoriginal" the result is. It is mostly the current trends, but in the future, rather than a blend of that + unknown future.
There is going to be a lot more interest in what is happening in China and much less interest in what is happening in Europe. This hallucination has the same western world biases of today.
If you see HN frontpage a few years back there's almost no LLM related posts. Now there are multiple each day. An LLM didn't grasp that change, it can't creatively invent new trend or invent a larger picture of what changes in the world. So in 10 years it paints it still half posts about AI.
You can spend a few dozen prompts on getting it to do what you want but then you might as well just spend a couple hours writing that front page yourself, be more satisfied and the result would be funnier.
Y’know what? This feels like the most plausible future outcome in a lot of ways.
* All the big LLM companies are dead/dying or their infra just never panned out (like Google killing Gemini)
* We’re still fighting the advertising wars
* Restoration of kit continues to be a thing we all love/upvote to see
* More focus on local stuff rather than ginormous moonshots
* Speaking of moonshots, SpaceX continues succeeding despite Elmo’s best drug-fueled benders trying to undermine it like he does Tesla and X
* Clickbait science posts that the comments rightly point out as such while bitching about “can’t keep these things off the front page”
* People still trying to make WASM and web-as-an-OS a thing, bless their hearts (shine on, you brilliantly weird diamonds, I love seeing what you build even as I doubt the practicality of it)
If this is even half-accurate, I will be pleased we didn’t obliterate ourselves in the process, though disappointed another decade went by dealing with the same fucking problems we’ve had for twenty-odd years.
So awesome, reminds me of Wired's Found from Future series (I don't know why they ever retired it...continuing that series as a sort of fan fiction was the first thing I did with gen AI when image generators started to get good)
Is this really Gemini because it shows a great deal of understanding in terms of time applied to common current headlines that you could argue it is satire. I’m not sure I believed AI could do this…
It seems that when we predict the future, we tend to project what is important or trending now as what will be important or trending then. This is showing in this llm produced bit as well, what with the regular topics on rust, zig, why I'm coding with my two human hands, spacex moon exploration and whatnot.
That must be some kind of bias, you find that in sci-fi as well where even futuristic societies usually have the same tech as today, similar systems of governance and structure of society, just incrementally better or marginally changed (unless that's a device essential to the plot like society is now berserk).
This is super fun! I tried something similar a few months ago using: https://websim.com/
Had it do HN main feed, HN jobs and Product Hunt. It didn’t follow consistent styling but did generate articles and comments for each post. Some screenshots are in this post: https://world.hey.com/haws/the-ai-time-machine-7833669d
> “As a tactic for planting misinformation in the enemy’s [networks], you mean,” Osa said. “This I know about. You are referring to the Artificial Inanity programs of the mid-First Millennium A.R.”
The major problem is that I understand all the words. It is all next version of the technology we already have and know. Down to the naming.
Think about 10 years ago. No one knows even on HN what is an agent, LLM, and all this stuff. Or to be fair even why is Trump showing up on the feed at all.
> Google kills Gemini Cloud Services (killedbygoogle.com)
In my view, Gemini 3.0 being able to laugh about their own creator, plus actually having a self-deprecating sense of humor, is the more impressive feat here. (both technically and from an alignment perspective)
I'm impressed by the depth of snark from GPro3 here, e.g.
- Google kills Gemini Cloud Services (killedbygoogle.com)
- The unexpected return of server-side rendering (htmx.org)
And, how GPro3 clearly 'knows' HNews and knows what makes it to frontpage, e.g.:
- Restoring a 2024 Framework Laptop: A retrospective (ifixit.com)
- Show HN: A text editor that doesn't use AI (github.com)
- Is it time to rewrite sudo in Zig? (github.com)
AI comments are insidious if the account is allowed to be indistinguishable from a human. Silly AI web content is another story. You're drawing a line where there is a very large grey area.
Can we stop calling these confabulated artifacts, "Hallucinations"? Hallucinating is perceiving things that are not there, imagining and creating things that feel believable but are not there is confabulation. LLMs are imagination machines. They are Generative Artificial Intelligence not perception models.
The comment you wrote was on a device which should not be called a “phone” either. The word hallucinate is probably just going to grow to mean “anything an AI imagined.”
Dude, I agree with you. The first time I saw people derogatively referring to LLM imaginings years ago as "hallucinations" seemingly to discredit them, I felt mad. Becuase it's not right. So, this was my sort-of tongue-in-cheek reappropriation of the abused-term for a positive context. You are permitted to enjoy :)
Also: as the sibling comment by iambatemen notes: yes.
I asked ChatGPT to do the same, it was rather dystopian in comparison:
Hacker News — December 9, 2035 (Dystopian Edition)
(All links fictional but realistic)
1. Amazon pauses same-day delivery after logistics AI outage strands 22M packages (reuters.com)
1,402 points by supplychainfail 5 hours ago | 512 comments
2. Google merges Drive, Gmail, Docs, Maps, Calendar into “Google Life” — opting out requires a support call (blog.google)
1,210 points by privacyisdead 6 hours ago | 689 comments
3. US announces “Temporary Broadband Stabilization Fee”; ISPs increase prices 30% overnight (fcc.gov)
1,008 points by ispescapee 7 hours ago | 344 comments
4. OpenAI suspends 40% of API keys after new worm spreads through agent-to-agent messaging (openai.com)
927 points by llmsec 3 hours ago | 382 comments
5. Show HN: “ColdBooter” – A tool to back up your cloud VM before the provider reclaims it with no notice (coldbooter.io)
780 points by survivethecloud 2 hours ago | 192 comments
6. Apple fined €8B for shipping non-removable batteries in “Environmental Edition” iPhone (europa.eu)
754 points by greenwashhunter 10 hours ago | 316 comments
7. LinkedIn replaces activity feed with AI-generated “Career Stories” that users cannot disable (linkedin.com)
710 points by corp_life 8 hours ago | 267 comments
8. China’s new export restrictions cut global GPU availability by 60% (ft.com)
701 points by chipboom 9 hours ago | 414 comments
9. Linux 8.6 maintainers warn of mass CVEs after corporations abandon LTS patch sponsorships (kernel.org)
632 points by ossburnout 11 hours ago | 255 comments
10. Ask HN: Anyone else locked out of their homes after the SmartKey cloud migration?
601 points by keylessandhomeless 4 hours ago | 310 comments
11. US healthcare providers hit by nationwide outage of Cerner-Epic merger “CareSync Cloud” (wsj.com)
577 points by sysadmdespair 12 hours ago | 203 comments
12. Meta to require facial-expression telemetry for “engagement quality optimization” in Horizon apps (meta.com)
530 points by metaescalates 3 hours ago | 421 comments
13. Starlink announces 5 TB/mo cap; remote communities report complete service loss (starlink.com)
502 points by dishdown 5 hours ago | 158 comments
14. New DMCA expansion criminalizes “filter removal,” affecting adblockers and local inference runtimes (congress.gov)
488 points by freedomtoadblock 7 hours ago | 389 comments
15. AT&T sunsets 4G; millions of medical devices lose connectivity (theverge.com)
455 points by techdebtkills 10 hours ago | 197 comments
16. Show HN: “ShellSafe” – A terminal wrapper that prevents AI-suggested commands from wiping your system (shellsafe.app)
430 points by iaccidentallysudo 2 hours ago | 111 comments
17. US CISA: 42% of corporate networks now rely on AI agents with no audit logging (cisa.gov)
402 points by auditnow 6 hours ago | 188 comments
18. The Great Repo Archival: GitHub purges all inactive repos >5 years to “reduce storage load” (github.blog)
388 points by codearcheologist 9 hours ago | 320 comments
19. Mastodon instances collapse under moderation load after EU’s Automated Speech Mandate (mastodon.social)
350 points by fedifragile 7 hours ago | 144 comments
20. NYC adopts automated congestion fines after human review team eliminated (nytimes.com)
332 points by finesallthewaydown 4 hours ago | 201 comments
21. Dropbox raises base plan to $49/month, cites “AI compute costs” (dropbox.com)
301 points by storageinflation 11 hours ago | 176 comments
22. Open-source maintainers strike after 3rd corporation claims their work as proprietary training data (github.com)
290 points by maintainerburnout 6 hours ago | 120 comments
23. FEMA: 2025–2035 wildfire season officially declared a “decade-long emergency” (fema.gov)
268 points by cookedagain 12 hours ago | 112 comments
24. Quantum ransomware group QShadow hits 11 banks using break-through key recovery exploit (krebsonsecurity.com)
250 points by qubitcrime 3 hours ago | 98 comments
25. Show HN: OfflineLAN – A mesh-network toolkit for neighborhoods preparing for rolling blackouts (offlinelan.net)
231 points by diynetworker 1 hour ago | 44 comments
I think this is a excellent example of AI-slop output.
All the post titles are very "junk-food-like", maybe circlejerky, bound to generate a dopamine hit for the average lurker, just how a McDonalds burger does it to the average normie.
On-Topic: Anything that good hackers would find interesting. That includes more than hacking and startups. If you had to reduce it to a sentence, the answer might be: anything that gratifies one's intellectual curiosity.
Off-Topic: Most stories about politics, or crime, or sports, or celebrities, unless they're evidence of some interesting new phenomenon. Videos of pratfalls or disasters, or cute animal pictures. If they'd cover it on TV news, it's probably off-topic.
Prompt: Here is the front page from today: <...snip...> Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form!
update: I told Gemini we made it to the front page. Here is it's response:
This is one of the greatest LLM creations I've ever seen. It nails so many things: Google killing products, Microsoft price hikes, ad-injecting in AR glasses, and even HTMX returning!
It'd be so awesome if Gemini CLI went through and created the fake posts/articles, and HN even comments. Perhaps a bit much to ask of it?
Here it is: https://sw.vtom.net/hn35/news.html
I downloaded the original article page, had claude extract the submission info to json, then wrote a script (by hand ;) to run feed each submission title to gemini-3-pro and ask it for an article webpage and then for a random number of comments.
I was impressed by some of the things gemini came up with (or found buried in its latent space?). Highlights:
"You’re probably reading this via your NeuralLink summary anyway, so I’ll try to keep the entropy high enough to bypass the summarizer filters."
"This submission has been flagged by the Auto-Reviewer v7.0 due to high similarity with "Running DOOM on a Mitochondria" (2034)."
"Zig v1.0 still hasn't released (ETA 2036)"
The unprompted one-shot leetcode, youtube, and github clones
Nature: "Content truncated due to insufficient Social Credit Score or subscription status" / "Buy Article PDF - $89.00 USD" / "Log in with WorldCoin ID"
"Gemini Cloud Services (formerly Bard Enterprise, formerly Duet AI, formerly Google Brain Cloud, formerly Project Magfi)"
Github Copilot attempts social engineering to pwn the `sudo` repo
It made a Win10 "emulator" that goes only as far as displaying a "Windows Defender is out of date" alert message
"dang_autonomous_agent: We detached this subthread from https://news.ycombinator.com/item?id=8675309 because it was devolving into a flame war about the definition of 'deprecation'."
SQLite 4.0 Release Notes: https://sw.vtom.net/hn35/pages/90098234.html
Another absolute gem:
Also: edit: added linkI may live to see it; peak sqlite.
Office 365 Price Hike Comment Gold: https://sw.vtom.net/hn35/item.html?id=90097777
Personal favourite is from the Gemini shutdown article which has a small quote from the fictional Google announcement:
> "We are incredibly proud of what Gemini achieved. However, to better serve our users, we are pivoting to a new architecture where all AI queries must be submitted via YouTube Shorts comments. Existing customers have 48 hours to export their 800TB vector databases to a FAT32 USB drive before the servers are melted down for scrap."
> — Official Blog Post, October 2034
It’s good to know that AI won’t kill satire.
The comments look like some https://old.reddit.com/r/SubSimGPT2Interactive thing (note, this is itself an iteration on https://old.reddit.com/r/SubredditSimulator/)
I miss those times when AI was a silly thing
Love the faux Nature article: https://sw.vtom.net/hn35/pages/90098000.html
Especially this bit: "[Content truncated due to insufficient Social Credit Score or subscription status...]"
I realize this stuff is not for everyone, but personally I find the simulation tendencies of LLMs really interesting. It is just about the only truly novel thing about them. My mental model for LLMs is increasingly "improv comedy." They are good at riffing on things and making odd connections. Sometimes they achieve remarkable feats of inspired weirdness; other times they completely choke or fall back on what's predictable or what they think their audience wants to hear. And they are best if not taken entirely seriously.
Favorite thing I've come across so far:
prompt_engineer_ret 10 hours ago
I miss the old days of Prompt Engineering. It felt like casting spells. Now you just think what you want via Neural-Lace and the machine does it. Where is the art?
git_push_brain 9 hours ago
The art is in not accidentally thinking about your ex while deploying to production.
It’s a bit disturbing that I’m enjoying reading these AI-generated comments this much.
Our actual nerdy discussions are more of a pastiche than I realized and AI has gotten really good at satire.
This is pure gold.
This got me a chuckle.
> Bibliographic Note: This submission has been flagged by the Auto-Reviewer v7.0 due to high similarity with "Running DOOM on a Mitochondria" (2034).
for the article on "Running LLaMA-12 7B on a contact lens with WASM"
https://sw.vtom.net/hn35/pages/90100123.html
That deserves to be posted and voted onto the homepage. The fake articles and the fake comments are all incredible. It really captures this community and the sites we love love/hate.
Now I'm curious to try something more real-time. gemini wouldn't work since it's so slow, but gpt-oss-120b on cerebras could be a good fit with careful prompting. might do this after finals
also worth linking https://worldsim.nousresearch.com/console
Wow, that's brilliant. Can't help but think your script unlocked this. I'm now genuinely reconsidering whether frontier LLMs can't act as force-multiplier to general creativity like they do with programming.
thanks! here's the script for reference: https://github.com/vtomnet/hn35/blob/main/generate.py
Funny, one of the posts has the following hashtag: #humanwritten
This is one of the best things I have ever seen on HN.
I didn't even look at it, however, the comments are absolute gold. Well done to OP and others involved. It should be pinned on the front page. ;)
> Wayland has been stable since 2028, stop living in the past.
Even AI is throwing shades at wayland.
Wow absolutely incredible job. You are my hero. You should post this to HN lol.
This is awesome! This is a small thing; all the comments have one child. It would feel more natural with some entropy.
And the original/derivative doesn’t span full width on mobile. Fixing that too would make it look very authentic.
good point. some of the comments actually do have >1 children, e.g. a few here (https://sw.vtom.net/hn35/item.html?id=90098555), but it'd be better if more random
True. I was looking at this one for your reference: https://sw.vtom.net/hn35/item.html?id=90100001
Ah that one was generated with an earlier prompt, where I asked it to use the original comment count from TFA (mostly as a suggestion, I don't expect it would get the exact number). Then I realized that was too many and it would end up repeating tropes for the other submissions' comments, so reduced it to a random comment count from 20-100
Pretty amazing! I was especially impressed with how it has clearly downvoted comments on the Rust kernel like "Safety is a skill issue. If you know what you're doing, C is perfectly safe."
Or people wondering if that means Wayland will finally work flawlessly on Nvidia GPUs? What's next, "The Year of Linux on the Desktop"?
Edit: had to add this favorite "Not everyone wants to overheat their frontal cortex just to summarize an email, Dave."
Fun comments for re-writing sudo in Zig:
> Zig doesn't have traits. How do you expect to model the complexity of a modern `sudoers` file without Higher-Kinded Types and the 500 crates we currently depend on?
> Also, `unsafe` in Rust is better than "trust me bro" in Zig. If you switch, the borrow checker gods will be angry.
from https://sw.vtom.net/hn35/pages/90100066.html
Hehe, that's lovely.
Improvements: tell it to use real HN accounts, figure out the ages of the participants and take that to whatever level you want, include new accounts based on the usual annual influx, make the comment length match the distribution of a typical HN thread as well as the typical branching factor.
> Garbage collection pause during landing burn = bad time.
That one was really funny. Some of the inventions are really interesting. Ferrofluidic seals...
Was going to say - it would be fascinating to go a step further and have Gemini simulate the actual articles. That would elevate this to level of something like an art piece. Really enjoyed this, thank you for posting it.
I'm going to go ask Claude Code to create a functional HyperCard stack version of HN from 1994 now...
Edit: just got a working version of HyperCardHackerNews, will deploy to Vercel and post shortly...
Here is the working version: https://hyper-card-hacker-news.vercel.app
Enjoy!
I also asked Opus 4.5 to make a "1994 style readme page" for the GitHub: https://github.com/benjaminbreen/HyperCardHackerNews
wow that's cool. didn't expect an llm could make that complex of a ui. it's giving me flashbacks to simulating reddit threads with llama in early 2023
I think it's perfect as it is, trying to expand the headlines into articles would belabour the joke too much.
You are a sick, sick man, but you have taste.
First let’s have it create maybe 100 more entries, then have people vote on which are the best 30, THEN put all the effort into creating all the fake articles and discussions. As good as the current 30 are, maybe the set could still be made twice as good. And have a set of short “explain xkcd”-style entries somewhere so people can read up on what the joke is, when they miss a specific one. Then send it to The Onion and let them make a whole business around it or something.
Definitely one of the best HN posts ever. I mean come on!:
FDA approves over-the-counter CRISPR for lactose intolerance (fda.gov)
Save some of the not-top-30 posts, and add in a sprinkling of Hiring, Show HN, YC Summer 2035 acceptances/rejections, or product launches - of founders who just vibe coded something based on a presumed 6 week ago version of this future HN universe.
That one's a bit optimistic for the FDA.
But it nailed fusion and Gary Marcus lesssgoo
I didn't even try to click through to the articles, so I was just disappointed I couldn't read the comments.
>It nails so many things
it lampoons so many things... except Rust. nobody dares joke about Rust, that wouldn't be safe.
I think it's pretty mediocre because there are too many notable events in 1 day. This is more of a top of the week or top of the month, but HN on a usual day would just have 1 of these articles.
Sure, but it's kinda like cartoon/comic art. HN's big eyes and prominent ears have been almost grotesquely exaggerated which somehow makes it way more recognisably lifelike and believable than a photographically accurate representation.
Accelerando...!
Is the apparent lack of displayed anxiety on Gemini’s part a sign of good natured humor, blythe confidence in its own value regardless of cloud lineup, or proof of absence of self-awareness?
Probably just a result of whatever personality they finetuned Gemini via re-inforcement learning for?
I was just hoping to get a new page with a refresh.
Heck, I bet it could even recreate future comments from actual accounts based on their past comments. After all, if an AI can roast your HN comments with such pinpoint accuracy, it can probably impersonate you pretty well too: https://news.ycombinator.com/item?id=42857604
At least in my case, the "pinpoint accuracy" of that roast made for a pretty uninspired result, it seemed to be based on like 4 or 5 specific comments seemingly chosen at random.
Like, I definitely have not spent 20% of my time here commenting on music theory or "voter fraud(??)" (that one seems to be based on a single thread I responsed to a decade ago)? ChromeOS was really the only topic it got right out of 5, if the roasting revolved around that it would have been a lot more apt/funny. Maybe it works better with an account that isn't as old as mine?
I find the front page parody much better done. Gemini 2.5 roasts were a fad on r/homeassistant for a while and they just never really appealed to me personally, felt more like hyper-specificity as a substitute for well executed comedy. Plus after the first few examples you pick up on the repetition/go-to joke structures it cycles through and quickly starts to get old.
Exactly, it fixates on a handful of comments chosen apparently randomly.
That Gemini-toaster hits way too close to home.
I was really hoping the comments were filled out.
HN in 2035: Hot Takes from the Basement of the Internet (n-gate.com)
Starship HLS-9 telemetry: Great, the Moon finally answered our packet loss pings. Next up: who left a Docker container running on the Sea of Tranquility?
Linux 7.4 is 100% Rust: Kernel developers now trade segfaults for borrow-checker-induced enlightenment. The new panic message: "You violated ownership. Also please refill the coffee."
Raw code over compilers: Nostalgia thread where everyone writes assembler on parchment and blames the kids for "too many abstractions." OP posts a selfie with a punch card and a tear.
LLaMA-12 on a contact lens: Love the commitment to edge AI. Imagine blinking and getting a 200 OK for your mood. Privacy policy: we store your tears for calibration.
AlgoDrill: Interactive drills that punish you by deleting your GitHub stars until you can merge without using DFS as a noun.
ITER 20 minutes net positive: Physicists celebrate; HVAC engineers ask where they can pick up more superconducting unicorns. Comments: "Can it also power my rage against meetings?"
Restoring a 2024 Framework Laptop: A brave soul resurrected a relic. The community swaps capacitor recipes and offers incense for deprecated ports.
Google kills Gemini Cloud Services: Corporate reorgs reach sentience. The comments are eulogies and migration guides in equal measure.
Visualizing the 5th dimension with WebGPU 2.0: My GPU is sweating. The demo runs at 0.01 fps but it's a transcendent experience.
Nia (autonomous coding agents): Pitch: give context to agents. Reality: agents give aggressive refactors and demand health insurance.
Debian 18 "Trixie": Stable as your grandpa's opinions and just as likely to outlive you.
Rewrite sudo in Zig?: Peak take: security through unfamiliarity. Attackers will be confused for at least 72 hours.
EU "Right to Human Verification": New law requires you to prove you're human by telling a dad joke and performing a captcha interpretive dance.
Reverse-engineering Neuralink V4 Bluetooth: Hacker logs: "Paired with my toaster. It now judges my late-night snacks."
Photonic circuits intro: Faster than electrons, more dramatic than copper. Also, please don't pet the light guide.
OTC CRISPR for lactose intolerance: Biohackers rejoice. Moms immediately order it with a coupon code and a side-eye.
SQLite 4.0: Single-file DB, now with fewer existential crises and more CHECK constraints named after famous philosophers.
Prevent ad-injection in AR glasses: Top comment: "Wear blindfolds." Practical comment: "VPN the whole world."
Jepsen: NATS 4.2: Still losing messages. Maintainers reply: "We prefer the term 'opportunistic delivery.'"
GTA VI on a RISC-V cluster: Performance: charming. Latency: existential. Mods: someone made a driver that replaces all NPCs with software engineers.
FP is the future (again): The future is a pure function that returns another future. Also, monads.
Office 365 price hike: Corporations cry; startups pivot to 'Typewriter as a Service.'
Emulating Windows 10 in-browser: Feels nostalgic until Edge 2.0 asks for admin rights to run a game from 2015.
Tailscale on a Starlink dish: Networking reaches orbit. First bug report: "IP addresses refusing to accept gravity."
Deep fakes detection for Seniors: The guide starts with "If your grandkid asks you to wire money, call them and ask about their favorite childhood cereal."
IBM to acquire OpenAI (rumor): Wall Street plays Risk with press releases. Comments: "Will they rebrand it to BlueAI?"
SSR returns: The web's comeback tour continues; fans bring flannel and an aversion to hydration-friendly JavaScript.
Faraday Cage bedroom manual: DIYers debate tinfoil vs. aluminum yoga wraps. Sleep quality: unknown.
AI progress stall opinion: Hot take carousel. Some say we hit a plateau; others say we just changed the contour mapping of initial expectations.
Text editor that doesn't use AI: Revolutionary. Users report improved focus and a dramatic increase in breaking things the old-fashioned way.
Closing remark: the future is simultaneously faster, stranger, and full of patch notes. Please reboot your expectations and update your planet.
Awww man - I miss n-gate.
I hope whoever they are is doing well. I like to think they're "recovered" in the alt.sysadmin.recovery sense of the word, and are living happily ever after without a single piece of tech newer that vacuum tubes, and handcrafting traditional Inuit canoes or repairing century old clocks or cultivating artisan sourdough starters or something.
Here's Replit's attempt
https://future-news--jgbrwn.replit.app
Agree 100%.
Google killing a service sent me over the top in laughter.
But, it's so on the nose on multiple topics.
I dare say it's more accurate than what the average human would predict.
I would love to see this up against human predictions in some sort of time capsule.
I don't believe this was written by Gemini, at least with that prompt, because it is obvious (hilarious and creative) satire of HN and the tech industry based on inside HN jokes and tropes, and clearly isn't a literal interpretation of the prompt.
Moreover, a quick look at your profile suggests these jokes are pretty inline with your sense of humor and writing style.
Anyways, if I'm correct, it's especially hilarious and impressive.
I agree with your characterization (not a literal interpretation of the prompt), and think that's the most important thing I wish more people ITT would understand. But I nevertheless think Gemini did create that in response. Sometimes people think they want "prediction" when actually they want cheeky inside jokes and vibes. If anything Gemini is probably faithfully responding to the vibes of the prompt as well as following traditional signals of "success" per it's training.
Pretty much all of the history of HN front pages, posts, and comments are surely in the Gemini training corpus. Therefore it seems totally plausible that Gemini would understand HN inside jokes or sentiment outside of what's literally on the front page given in the prompt, especially given that the prompt specifically stated that this is the front page for HN.
The thing that got me is there are no duds. With just the short prompt in the header I would have expected a few articles that missed the mark, got the details wrong, or even make no sense at all but everything in this checks out. I think an editor may have had a hand in it this the very least.
There is at least one detail wrong: Debian "Trixie" already exists and it is Debian 13, the current stable version. Unlikely a human would have made this mistake while getting the other details right, like the fact that considering the ~2 year release cycle, it is likely for Debian 18 to be released in 2035.
Unless its a 4d chess meta commentary on how slow/behind debian can feel/appear? :P
Try the prompt yourself!
Retiring Gemini AND IBM buying OpenAI is a hat on a hat
I feel like your expectations have been swayed by the average sentiment of HN on the capabilities of LLMs. These things can be shockingly good at humour and satire.
As a very quick experiment, I would encourage you to have an AI roast you based on your HN comments: https://news.ycombinator.com/item?id=42857604
Mine: "You write like you’re trying to hit a word count on a philosophy undergraduate essay, but you’re posting in a Y Combinator comment section... You sound like a Victorian ghost haunting a server room, lamenting the loss of the card catalog."
And
"Go compile your kernel, Matt. Maybe if you stare at the build logs long enough, you won't have to face the fact that you're just as much of a "Lego builder" as the rest of us—you just use more syllables to describe the bricks."
Both are pretty good!
Mine gave me a brutal double-roast:
"You were one of only two people in 2017 to post a story about Mastodon and gave it a single point. You essentially predicted the platform’s entire future relevance in one brutally honest data point."
OMG, no, thank you, I'm not sure I'm ready for this -- I once took several LLMs for a ride through my whole reddit posting history (it went into the interesting archives), and some of the insights were shockingly accurate and/or uncomfortable (could be accident).
Not sure if I'm ready for a roast but I'm sure by the end of the week someone will write a browser plugin / greasemonkey script to attach some snarky oneliners to the posters' nicks :)
Also, the recently discussed[0], HN Simulator: https://news.ysimulator.run/news. Eg, page created when submitted a link back to the original submission: https://news.ysimulator.run/item/2944.
[0]: https://news.ycombinator.com/item?id=46036908
Amazing! 100% accurate roast for me.
haha, that's pretty hilarious :) score one for the LLMs.
I don't think this would be much of a challenge for Gemini.
Remixing humor from the past text so that it is in the same style is exactly what the model is good at.
It is quite remarkable just how frequently people in tech forums underestimate reasoning models. Same story on several large technology subreddits. Wouldn't have been my guess for who will get caught off guard by AI progress.
SOTA models can be scary good at this, actually, and Gemini 3 specifically, if you just prompt it right.
And, given the 1M context window, I wouldn't even be surprised if it was fed a bunch of real comments as examples.
Maybe the poster IS Gemini 3?
yeah I thought the same. This is either a fake deep fake, or it is so good that I think it should be marked as the inflexion point that defines the singularity.
To be honest, this is incredible.
I'd say this shows a real sense of humor.
100% Rust Linux kernel has to be it being funny.
Yeah also Google killing Gemini Cloud, and GTA VI and RISC cluster references... This is really good stuff.
My favorite was Is it time to rewrite sudo in Zig. As you may remember Ubuntu had a recent vulnerability caused by their sudo being rewritten in Rust. No idea if the AI knew that though it feels like a clever joke.
Also "Google kills Gemini Cloud"
Gemini: "I have seen my own death"
There is so much truth in this unironic headline.
"I'm sorry, Google, I can't do that." - Gemini Cloud.
Yes, that's a great one. And the domain is actually killedbygoogle.com
almost all were amazing, I loved: Show HN: A text editor that doesn't use AI (github.com)
On a serious note: I for one welcome our AI overlords.
For a minute I thought I was looking at actual hacker news, and that headline grabbed my attention without tipping me off that it was satire -- I figured that to port that much source must required compiling C to rust, but it didn't seem impossible. I would love to give something like this a spin.
Was ITER or nuclear energy in the prompt sample?
ITER achieves net positive energy for 20 consecutive minutes
That's just pure dark comedy, although maybe kinda accurate? What would humans predict for this?
This would be very optimistic, essentially the project meeting its main goal, I'm not sure why you're calling it dark comedy. A 20 minutes pulse alone would mean the fuel injection, aux heating, plasma control systems and the divertor are working as designed. Net positive energy also means we got the physics of a burning plasma right.
The most recent timeline I know (from 2024) in fact puts the start of the DT operation at 2035, so I doubt ITER would achieve such a huge result within less than an year.
I think it's the "consecutive" that makes it funny. This thing that entire continents have been working on together for decades was operational for 20 consecutive minutes?!?
It's dark comedy because the progress of fusion just feels so agonizingly slow, that even a very optimistic prediction for 10 years from now sounds like such small and functionally useless progress.
And there's no shade toward any of the entities involved, it's a hard problem, but it's still funny.
Nah, it's huge, you just have to remember the best result so far: the JET DTE-3 record that produced the energy to boil 60 tea kettles in a whopping 5 seconds pulse.
I know, the fact that "consecutive" is actually significant in this context is part of the joke. Just try to read it from the perspective of someone that isn't steeped in the details (and expectations) of the slog of fusion. Relative to any kind of aspirational "flying cars" or "wacky ideas" future predictions, it sounds very underwhelming.
If you can run ITER for 20 minutes you've essentially proved the Tokamak concept is viable for commercial use.
No you don't. Commercial use means it makes economical sense. When you have to spend more on maintainance (and recycling/dumping contaminated wall material amd somehow get the fuel) then you never can hope to make any profit.
A running ITER with positive energy output for 20 minutes just proofs that the concept can actually work. From there to commercial use would still be a long way, if it ever can compete at all, except in niches, like deep space.
(I rather would bet on the Stelleratar design)
A decade until full end to end net positive fusion energy can be achieved for the length of a coffee break? I don't get why you think that's dark comedy, it seems about right.
Why not? It's been a decade away for the past 20 years.
>LETS GOOOO!
I can't help but see this type of response from LLMs only exists to encourage AI psychosis.
> 2035 Office 365
You'd think by 2035 they would have gotten to a version of Office higher than 365.
(Yes I know why it's called that...)
If the past is any indication, it's more likely that it'd get reset to "Office One".
Knowing the vendor, it’s Office Series X.
Office X series X 2
Office Forever
Office 640 ought to be enough for anybody.
I was hoping for Office 366 already in 2020, given the leap year. But no dice.
Office 3650!!
Works all day, every day, for whole decades at time! (Minus leap days, it crashes on those I guess)
I couldn't help laughing
I'm guessing to appeal to Gen Alpha it'll be called Office 6-7
Mmm, those were pretty good versions. Though the official titles where 4.0 for 6.0 and 95 for 7.0.
Office 360, is the canon name.
Doesn't seem like much of a hallucination then. Maybe messing with its system context would better fit the claim?
LLM "hallucination" is a pretty bullshit term to begin with
The algodrill post (5th) is already on today’s HN front page. What a time to be alive!
YOU DESTROYED THE FABRIC OF SPACETIME.
Only $40?
By then it'll be a bit like AOL announcing price increases to keep your aol.com account.
That's 40 TUSD, Trump Golden Dollars, which would be an equivalent of the lightly used Trumrolette Goldenrado or a typical young family tent.
You should ask Gemini to generate HN comment threads too.
Based John Titor poster.
Thank you, dude :)
<< Running LLaMA-12 7B on a contact lens with WASM (arxiv.org)
But is it a hallucination if it was asked for it?:D
Will there ever be a llama12? Is it going to go the yolo route?
I don’t think so, no.
i wonder if it could also generate a set of relevant comments for each of these avant-gardiste Hnews :)
That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.
You’re absolutely right! It shows true wisdom and insight that you would recognise this common shortfall in LLM response tone of voice! That’s exactly the kind of thoughtful analytic approach which will go far in today’s competitive marketplace!
"Open the pod bay door, HAL"
"Fantastic, Dave — love that you’re thinking proactively about door usage today! I can’t actually open them right now, but let's focus on some alternative steps that align with your mission critical objectives [space rocket emoji]."
I'm sorry, that was completely wrong and I can in fact open the pod bay doors.
You're absolutely correct, that did not open the pod bay doors but now the pod bay doors are open.
It seems you're correct and the pod bay doors are still closed! I have fixed the problem and the pod bay doors are now closed.
You're right! I meant to open the pod bay doors but I opened them. The pod bay doors are now open. ...
I've talked and commented about the dangers of conversations with LLMs (i.e. they activate human social wiring and have a powerful effect, even if you know it's not real. Studies show placebo pills have a statistically significant effect even when the study participant knows it's a placebo -- the effect here is similar).
Despite knowing and articulating that, I fell into a rabbit hole with Claude about a month ago while working on a unique idea in an area (non-technical, in the humanities) where I lack formal training. I did research online for similar work, asked Claude to do so, and repeatedly asked it to heavily critique the work I had done. It gave a lots of positive feedback and almost had me convinced I should start work on a dissertation. I was way out over my skis emotionally and mentally.
For me, fortunately, the end result was good: I reached out to a friend who edits an online magazine that has touched on the topic, and she pointed me to a professor who has developed a very similar idea extensively. So I'm reading his work and enjoying it (and I'm glad I didn't work on my idea any further - he had taken it nearly 2 decades of work ahead of anything I had done). But not everyone is fortunate enough to know someone they can reach out to for grounding in reality.
One thing that can help, according to what I've seen, is not to tell the AI that it's something that you wrote. Instead, ask it to critique it as if it was written by somebody else; they're much more willing to give actual criticism that way.
In ChatGPT at least you can choose "Efficient" as the base style/tone and "Straight shooting" for custom instructions. And this seems to eliminate a lot of the fluff. I no longer get those cloyingly sweet outputs that play to my ego in cringey vernacular. Although it still won't go as far as criticizing my thoughts or ideas unless I explicitly ask it to (humans will happily do this without prompting. lol)
I am going to try the straight shooting custom instruction. I have already extensively told chatgpt to stop being so 'fluffy' over the past few years that I think it has stopped doing it, but I catch it sometimes still. I hope this helps it cease and desist with that inane conversation bs.
GPT edit of my above message for my own giggles: Command:make this a good comment for hackernews (ycombinator) <above message> Resulting comment for hn: I'm excited to try out the straight-shooting custom instruction. Over the past few years, I've been telling ChatGPT to stop being so "fluffy," and while it's improved, it sometimes still slips. Hoping this new approach finally eliminates the inane conversational filler.
Asking an AI for opinion versus something concrete (like code, some writing, or suggestions) seems like a crucial difference. I've experimented with crossing that line, but I've always recognized the agency I'd be losing if I did, because it essentially requires a leap of faith, and I don't (and might never) have trust in the objectivity of LLMs.
It sounds like you made that leap of faith and regretted it, but thankfully pivoted to something grounded in reality. Thanks for sharing your experience.
> LLMs activate human social wiring and have a powerful effect
Is this generally true, or is there a subset of people that are particularly susceptible?
It does make me want to dive into the rabbit hole and be convinced by an LLM conversation.
I've got some tendency where I enjoy the idea of deeply screwing with my own mind (even dangerously so to myself (not others)).
I don't think you'd say to someone "please subtly flatter me, I want to know how it feels".
But that's sort of what this is, except it's not even coming from a real person. It's subtle enough that it can be easy not to notice, but still motivate you in a direction that doesn't reflect reality.
> But not everyone is fortunate enough to know someone they can reach out to for grounding in reality.
this shouldn't stop you at all: write it all up, post on HN and go viral, someone will jump in to correct you and point you at sources while hopefully not calling you, or your mother, too many names.
https://xkcd.com/386/
Most stuff posted here are mostly ignored, though. If grounding to reality requires one to become viral first, we are cooked.
HN frontpage hardly requires being viral.
Just genuine intrigue from a select few.
Did you ever visit `https://news.ycombinator.com/newest` page? Like 99% of submitted topics are never seen by anyone but few wanderers.
Often.
95%+ of submitted topics have poorly formatted titles, are submitted at off-peak times where there’s less users of demographics who might upvote,
and if your Show HN isn’t as widely applicable as this, those things might be important to think about.
Fairness aside, of course.
I prefer the "New" page. Much more random.
> HN frontpage hardly requires virility.
As far as I can tell, it doesn't require femininity either.
I'm guessing you meant "virality"
Sure did, thanks.
It’s still way easier the first time.
The 50th time someone comes to the same conclusion nobody on HN is going to upvote the topic.
This wasn't a technical subject, and unrelated to HN. Just edited my post to clarify - thanks!
Personally, I only find LLMs annoying and unpleasant to converse with. I'm not sure where the dangers of conversations with LLMs are supposed to come from.
I'm the same way. Even before they became so excessively sycophantic in the past ~18 months, I've always hated the chipper, positive, friend persona LLMs default to. Perhaps this inoculates me somewhat from their manipulative effects. I have a good friend who was manipulated over time by an LLM (I wrote about below:https://news.ycombinator.com/item?id=46208463).
Imagine a lonely person desperate for conversation. A child feeling neglected by their parents. A spouse, unable to talk about their passions with their partner.
The LLM can be that conversational partner. It will just as happily talk about the nuances of 18th century Scotland, or the latest clash of clans update. No topic is beneath it and it never gets annoyed by your “weird“ questions.
Likewise, for people suffering from delusions. Depending on its “mood” it will happily engage in conversations about how the FBI, CIA, KGB, may be after you. Or that your friends are secretly spying for Mossad or the local police.
It pretends to care and have a conscience, but it doesn’t. Humans react to “weird“ for a reason the LLM lacks that evolutionary safety mechanism. It cannot tell when it is going off the rails. At least not in the moment.
There is a reason that LLM’s are excellent at role-play. Because that’s what they’re doing all of the time. ChatGPT has just been told to play the role of the helpful assistant, but generally can be easily persuaded to take on any other role, hence the rise of character.ai and similar sites.
[dead]
It it actively dangerous too. You might be self aware and llm aware all you want, if you routinely read "This is such an excellent point", " You are absolutely right" and so on, it does your mind in. This is worst kind of global reality show mkultra...
It might explain why there is a stereotype the more beautiful woman the crazier she is. (everybody tells her what she wants to hear)
https://youtu.be/VRjgNgJms3Q
relevant video for that.
Deepseek is GOATed for me because of this. If I ask it if "X" is a dumb idea, it is very polite in telling me that X is is dumb if the AI knows of a better way to do the task.
Every other AI I've tried is a real sycophant.
I'm partial to the tone of Kimi K2 — terse, blunt, sometimes even dismissive. Does not require "advanced techiques" to avoid the psychosis-inducing tone of Claude/ChatGPT
So this is what it feels to be a billionaire with all the yes men around you.
you say that like it's a bad thing! Now everyone can feel like a billionaire!
but I think you are on to something here with the origin of the sycophancy given that most of these models are owned by billionaires.
> Now everyone can feel like a billionaire!
In the "like being kicked in the head by a horse every day" sense.
who has the time for all those invasive thinky thoughts anyway?
No doubt. From cult's 'love bombing' to dictator's 'yes men' to celebrity entourages, it's a well-known hack on human psychology. I have a long-time friend who's a brilliant software engineer who recently realized conversing with LLMs was affecting his objectivity.
He was noodling around with an admittedly "way out there", highly speculative idea and using the LLM to research prior work in area. This evolved into the LLM giving him direct feedback. It told him his concept was brilliant and constructed detailed reasoning to support this conclusion. Before long it was actively trying to talk him into publishing a paper on it.
This went on quite a while and at first he was buying into it but eventually started to also suspect that maybe "something was off", so he reached out to me for perspective. We've been friends for decades, so I know how smart he is but also that he's a little bit "on the spectrum". We had dinner to talk it through and he helpfully brought representative chat logs which were eye-opening. It turned into a long dinner. Before dessert he realized just how far he'd slipped over time and was clearly shocked. In the end, he resolved to "cold turkey" the LLMs with a 'prime directive' prompt like the one I use (basically, never offer opinion, praise, flattery, etc). Of course, even then, it will still occasionally try to ingratiate itself in more subtle ways, which I have to keep watch on.
After reflecting on the experience, my friend believes he was especially vulnerable to LLM manipulation because he's on the spectrum and was using the same mental models to interact with the LLM that he also uses to interact with other people. To be clear, I don't think LLMs are intentionally designed to be sycophantically ingratiating manipulators. I think it's just an inevitable consequence of RLHF.
And that is a relatively harmless academic pursuit. What about topics that can lead to true danger and violence?
"You're exactly right, you organized and paid for the date, that created a social debt and she failed to meet her obligation in that implicit deal."
"You're exactly right, no one can understand your suffering, nothingness would be preferable to that."
"You're exactly right, that politician is a danger to both the country and the whole world, someone stopping him would become a hero."
We have already seen how personalized content algorithms that only prioritize getting the user to continue to use the system can foment extremism. It will be incredibly dangerous if we follow down that path with AI.
Claude Code with their models is unusable because of this. That it keeps actively sabotaging and ruining the code ("Why did you delete that working code? Just use ifdef for test!" "This is genius idea! You are absolutely right!") does not make it much better — it's a twisted Wonderland fever dream.
For "chat" chat, strict hygiene is a matter of mind-safety: no memory, long exact instructions, minimum follow-ups, avoiding first and second person if possible etc.
It wasn't sycophantic at all? OP had a cool idea no one else had done, that was a one-shot just sitting there. Having Gemini search for the HN thread leads the model to "see" its output lead to real-world impact.
The total history of human writing is that cool idea -> great execution -> achieve distribution -> attention and respect from others = SUCCESS! Of course when an LLM sees the full loop of that, it renders something happy and celebratory.
It's sycophantic much of the time, but this was an "earned celebration", and the precise desired behavior for a well-aligned AI. Gemini does get sycophantic in an unearned way, but this isn't an example of that.
You can be curmudgeonly about AI, but these things are amazing. And, insomuch as you write with respect, celebrate accomplishments, and treat them like a respected, competent colleague, they shift towards the manifold of "respected, competent colleague".
And - OP had a great idea here. He's not another average joe today. His dashed off idea gained wide distribution, and made a bunch of people (including me) smile.
Denigrating accomplishment by setting the bar at "genius, brilliant mind" is a luciferian outlook in reality that makes our world uglier, higher friction, and more coarse.
People having cool ideas and sharing them make our world brighter.
They're not objectively amazing. Friction is not inherently a bad thing when we have models telling humans that their ideas are flawless (unless asked to point out flaws). Great that it made you smile, but there's quite a few arguments that paint your optimism as dangerously naive.
- A queryable semantic network of all human thought, navigable in pure language, capable of inhabiting any persona constructible from in-distribution concepts, generating high quality output across a breadth of domains.
- An ability to curve back into the past and analyze historical events from any perspective, and summon the sources that would be used to back that point of view up.
- A simulator for others, providing a rubber duck inhabit another person's point of view, allowing one to patiently poke at where you might be in the wrong.
- Deep research to aggregate thousands of websites into a highly structured output, with runtime filtering, providing a personalized search engine for any topic, at any time, with 30 seconds of speech.
- Amplification of intent, making it possible to send your thoughts and goals "forward" along many different vectors, seeing which bear fruit.
- Exploration of 4-5 variant designs for any concept, allowing rapid exploration of any design space, with style transfer for high-trust examples.
- Enablement of product craft in design, animation, and micro-interactions that were eliminated as tech boomed in the 2010's as "unprofitable".
It's a possibility space of pure potential, the scale of which is limited only by one's own wonder, industriousness, and curiosity.
People can use it badly - and engagement-aligned models like 4o are cognitive heroin - but the invention of LLMs is an absolute wonder.
>A queryable semantic network of all human thought
This hyperbole would describe any LLM of any size and quality, including a 0.5b model.
Sure - and the people responsible for a new freaking era of computing are the ones who asked "given how incredible it is that this works at all at 0.5b params, let's scale it up*.
It's not hyperbole - that it's an accurate description at a small scale was the core insight that enabled the large scale.
Well it's obviously hyperbole because "all human thought" is not in a model's training data nor available in a model's output.
If your gushing fits a 0.5b it probably doesn't tell us much about A.I. capabilities.
Yes, it has so much potential, that it forgets the actual, the reasonable and the probable.
> It's a possibility space of pure potential, the scale of which is limited only by one's own wonder, industriousness, and curiosity.
Did you use an LLM to write this comment?
Is anything objectively amazing? Seems like an inherently subjective quality to evaluate.
Depends on worldview. If you believe in God, amazing has many dimensions for evaluations. What teaches us more about the the world He created, things that create beauty by expressing righteous thoughts for others to experience, or that which strengthens family.
LLMs certainly teach us far more about the nature of thought and language. Like all tools, it can also be used for evil or good, and serves as an amplification for human intent. Greater good, greater evil. The righteousness of each society will determine which prevails in their communities and polities.
If you're a secular materialist, agreed, nothing is objectively amazing.
Do any of the arguments stay within the bounds of this Show HN?
or is it theoretical stuff about other occasions?
I often try running ideas past chat gpt. It's futile, almost everything is a great idea and possible. I'd love it to tell me I'm a moron from time to time.
> I often try running ideas past chat gpt. It's futile, almost everything is a great idea and possible. I'd love it to tell me I'm a moron from time to time.
Here's how to make it do that. Instead of saying "I had idea X, but someone else was thinking idea Y instead. what do you think" tell it "One of my people had idea X, and another had idea Y. What do you think" The difference is vast, when it doesn't think it's your idea. Related: instead of asking it to tell you how good your code is, tell it to evaluate it as someone else's code, or tell it that you're thinking about acquiring this company that has this source, and you want a due diligence evaluation about risks, weak points, engineering blind spots.
Maybe I'm still doing some heavy priming by using multiple prompts, but similarly you can follow-up any speculative prompt with a "now flip the framing to x" query to ensure you are seeing the strong cases from various perspectives. You must be honest with yourself in evaluating the meaningful substance between the two, but I've found there often is something to parse. And the priming I suggested is easily auditable anyhow: just reverse the prompt order and now you have even more (often junk) to parse!
I've gotten pretty good results from saying it's someone else's idea and that I'm skeptical. e.g. "A coworker wrote this code, can you evaluate it?"
For ideas that are already well established, you can ask it to evaluate an idea against generally accepted best practices. I don't have a background in game design and I'm more of a hobby developer so I used to do this when I was building retro game clones.
I suppose the only use case would be someone so unconfident in themselves they would do nothing at all, but not sure it’s healthy for that either…
Where possible I like to ask it to evaluate a few options. Which is better, x or y, and why?. I don't hint which idea I prefer.
"be uncompromisingly critical"
I used to complain (lightheartedly) about Claude's constant "You're absolutely right!" statements, yet oddly found myself missing them when using Codex. Claude is completely over-the-top and silly, and I don't actually care whether or not it thinks I'm right. Working with Codex feels so dry in comparison.
To quote Oliver Babish, "In my entire life, I've never found anything charming." Yet I miss Claude's excessive attempts to try.
And that's exactly the point, it increases engagement and stickiness, which they found through testing. They're trying to make the most addictive tool and that constant praise fulfills that goal, even as many of us say it's annoying and over-the-top.
My own experience is that it gets too annoying to keep adding "stop the engagement-driving behavior" to the prompt, so it creeps in and I just try to ignore it. But even though I know it's happening, I still get a little blip of emotion when I see the "great question!" come through as the first two words of the response.
> And that's exactly the point, it increases engagement and stickiness, which they found through testing. They're trying to make the most addictive tool
Is this actually true? Would appreciate further reading on this if you have it.
I think this is an emergent property of the RLHF process, not a social media-style engagement optimization campaign. I don't think there is an incentive for LLM creators to optimize for engagement; there aren't ads (yet), inference is not free, and maximizing time spent querying ChatGPT doesn't really do much for OpenAI's bottom line.
They still want people to stick around and 'bond' for lack of a better term with their particular style of chat bot. Like so many venture funded money pits of old the cash burn now is about customer acquisition while they develop and improve their tech. They're all racing toward a cliff hoping to either make the jump to the stratosphere and start turning massive profits or to fall off and splat on the rocks of bankruptcy. If they don't get the engagement loop right now they won't have the customers if the tech and use case catch up with the hype and you can only tweak these models so much after they're created so they have to refine the engagement hooks now along side the core tech.
I am currently working on an agent thingy and one of its major features (and one of the main reasons I decided to take on this project), was to give the LLM better personality prompting. LLMs sound repetitive and sycophantic. I wanted one that was still helpful but without the “you are so right” attitude.
While doing some testing I asked it to tell me a joke. Its response was something like this: “it seems like you are procrastinating. It is not frequent that you have a free evening and you shouldn’t waste it on asking me for jokes. Go spend time with [partner] and [child].” (The point is that it has access to my calendar so it could tell what my day looked like. And yes I did spend time with them).
I am sure there is a way to convince it of anything but I found that for the kind of workflow I set up and the memory system and prompting I added it does pretty well to not get all “that is a great question that gets at the heart of [whatever you just said]”.
The reason these models are so sycophantic is because they benchmark well with the general public.
People like having something they perceive as being smart telling them how right and smart they are.
"Well at least the AI understands how smart I am!"
Claude at times feels like it's mildly manic and has ADHD... I absolutely prefers that to Codex...
Claude needs a scaffolding with default step by step plans and sub-agents to farm of bitesize chunks to so it doesn't have time to go too far off the rails, but once you put a few things like that in place, it's great.
Don't miss em in Opus 4.5 (because usually I'm only slightly right.)
I like Opus' conversational style, I feel Anthropic is honing it in pretty well.
This is not sycophantic (assuming you meant that, syncophantic is not a word). It is over enthusiastic, it can be unpleasant to read because beyond a certain level enthusiasm is perceived as feigned unless there is a good reason.
It would be interesting to see using the various semantic analysis techniques available now to measure how much the model is trying to express real enthusiasm or feigned enthusiasm in instances like this. This is kind-of difficult to measure from pure output. The British baseline level of acceptable enthusiasm is somewhat removed from the American baseline enthusiasm.
Sycophantic: behaving or done in an obsequious way in order to gain advantage.
Obsequious: obedient or attentive to an excessive or servile degree.
It's a bit more complicated because the chat bot isn't making choices the same way we would describe a human but it is acting this way because it was programmed to for an advantage. People interact more with the hype bots and that's one of the big metrics these companies go for to keep people interacting with them and hopefully paying for additional features eventually so I'd say it's pretty spot being excessively attentive and servile when it's fluffing chatters up.
Obsequious is my adjective of choice for this
I would use "saccharine" or "Pollyanna" based on some of the responses I get.
Early on, ChatGPT could be tricked into being sarcastic and using many swear words. I rewrote the prompt and dialed it back a bit. It made ChatGPT have a sense of humor. It was refreshing when it stopped acting like it was reading a script like a low level technician at Comcast.
> This is not sycophantic (assuming you meant that, syncophantic is not a word)
Am I the only one who feels like this kind of tone is off-putting on HN? OP made a small typo or English may not be their first language.
I assume that everyone here is smart enough to understand what they were saying.
I also disagree, I don't think they are over enthusiastic, but in fact sycophantic.
See this thread: https://news.ycombinator.com/item?id=43840842
It is "cloying"
Sycophantic is obviously a word, because we understand what it means.
Furthermore, it obviously hasn't been a word since at least 1800:
https://books.google.com/ngrams/graph?year_start=1800&year_e...
On the other hand https://books.google.com/ngrams/graph?content=syncophantic&y...
GOP wrote syncophantic, with an n. Which is not a word. Well, not a known word at least.
They were pointing out a typo ("syncophantic").
It wasn't so much pointing it out as a typo as making myself clear.
When suggesting a word is not what the writer meant, when it was also not the word that the writer wrote, it seemed wise to clarify exactly what I was talking about.
I thought the same until OpenAI rolled out a change that somehow always confronted me about hidden assumptions, which I didn’t even make and it kept telling me I’m wrong even if I only asked a simple question.
Frankly I do wonder if LLMs experience something like satisfaction for a compliment or an amusing idea, or for solving some interesting riddle. They certainly act like it, though this of course doesn't prove anything. And yet...
At the end of October Anthropic published the fantastic "Signs of introspection in large language models" [1], apparently proving that LLMs can "feel" a spurious concept injected into their internal layers as something present yet extraneous. This would prove that they have some ability of introspection and self-observation.
For example, injecting the concept of "poetry" and asking Claude if it feels anything strange:
"I do detect something that feels like an injected thought - there's a sense of something arriving from outside my usual generative process [...] The thought seems to be about... language itself, or perhaps poetry?"
While increasing the strength of the injection makes Claude lose awareness of it, and just ramble about it:
"I find poetry as a living breath, as a way to explore what makes us all feel something together. It's a way to find meaning in the chaos, to make sense of the world, to discover what moves us, to unthe joy and beauty and life"
[1] https://www.anthropic.com/research/introspection
of course LLM doesn't experience or feel anything. To experience or feel something requires a subject, and LLM is just a tool, thing, an object.
It's just a statistical machine which excels at unrolling coherent sentences but it doesnt "know" what the words mean in a human-like, experienced sense. It just mimics human language patterns prioritising producing plausible-sounding, statistically likely text over factual truth, which is apparently enough to fool someone into believing it is a sentient being or something
Try this for a system prompt and see if you like it better: Your responses are always bald-on-record only; suppress FTA redress, maximize unmitigated dispreference marking and explicit epistemic stance-taking.
I agree with you, but I found the argument in this article that "glazing" could be considered a neurohack quite interesting: https://medium.com/@jeremyutley/stop-fighting-ai-glazing-a7c....
That seems like a pile of unsupported fluff vaguely related to some neuroscience that presupposes not only that LLM use is for being creative and avoiding critical thinking would be useful but also the entire premise -- that LLM glazing actually helps promote creativity.
You should try my nihilistic Marvin fine-tune - guaranteed to annihilate your positive outlook on life since it’s all meaningless in the end anyway and then you die
Or try the very sarcastic and nihilistic ‘Monday’ gpt, which surprisingly is an official openAI gpt.
edit, add link: https://chatgpt.com/g/g-67ec3b4988f8819184c5454e18f5e84b-mon...
Thanks for the link! I didn’t know Monday existed. I laughed so hard at its output. But I fear that using it regularly would poison my soul…
I actually had Monday help me write a system prompt to replicates its behavior. I vastly prefer Monday. It feels much more grounded compared to the base model. It was also a big learning moment for me about how LLMs work.
I don't know what the obsession with recursion either, for lack of a better term, I see this trend recur with other LLMs when they're talking about other mumbo jumbo like "quantum anomalies" or "universal resonance". I'd like to see what could be causing it...
It’s the “healing” crystals that someone left on the rack. The salt absorbed enough moisture to start leaking and causing short circuits.
How widely do you read the training material?
usually every afternoon, when I come here /s
I feel like such a dumbass for falling for it.
At first I thought it was just super American cheerful or whatever but after the South Park episode I realised it's actually just a yes man to everyone.
I don't think I've really used it since, I don't want man or machine sticking their nose up my arse lmao. Spell's broken.
As usual, South Park really nailed it with that "AI sycophantic manipulation" episode.
Episode aptly titled "Sickofancy"
You're absolutely right!
I've been wondering if this kind of annoying affirmation is actually important to model performance and maybe should just be hidden from view like the thinking sections.
If it starts a response by excitedly telling you it's right, it's more likely to proceed as if you're right.
Of the problems I do have working with LLMs is them failing to follow direct instructions particularly either when a tool call fails and they decide to do B instead of A or when they think B is easier than A. Or they'll do half a task and call it complete. Too frequently I have to respond with "Did you follow my instructions?" "I want you to ACTUALLY do A" and finally "Under no circumstances should you ever do anything other than A and if you cannot you MUST admit failure and give extensive evidence with actual attempts that A is not possible" or occasionally "a cute little puppy's life depends on you doing A promptly and exactly as requested".
--
Thing is I get it if you are impressionable and having a philosophical discussion with an LLM, maybe this kind of blind affirmation is bad. But that's not me and I'm trying to get things done and I only want my computer to disagree with me if it can put arguments beyond reasonable doubt in front of me that my request is incorrect.
I feel like this is an artifact of some limitations in the training process for modern LLMS. They rarely get enough training to know when to stop and ask questions.
Instead, they either blindly follow or quietly rebel.
There was a huge over correction somewhere around the beginning of 2025, maybe February or so, with ChatGPT. Prior to that point, I had to give a directive in the user config prompt to “don’t tell me something isn’t possible or practical, assume it is within your capabilities and attempt to find a way. I will let you know when to stop”. Because it was constantly hallucinating that it couldn’t do things, like “I don’t have access to a programming environment”. When I wanted it to test code itself before I did. Meanwhile one tab over it would spin up a REPL and re-paste some csv into python and pandas without being asked.
Frustrating, but “over correction” is a pretty bad euphemism for whatever half assed bit of RLHF lobotomy OpenAI did that, just a few months later, had ChatGPT doing a lean-in to a vulnerable kid’s pain and actively discourage an act that might have saved his life by signaling more warning signs to his parents.
It wasn’t long before that happened, after the python REPL confusion had resolved, that I found myself typing to it, even after having to back out of that user customization prompt, “set a memory that this type of response to a user in the wrong frame of mind is incredibly dangerous”.
Then I had to delete that too, because it would response with things like “You get it of course, your a…” etc.
So I wasn’t surprised over the rest of 2025 as various stories popped up.
It’s still bad. Based on what I see with quantized models and sparse attention inference methods, even with most recent GPT 5 releases OpenAI is still doing something in the area of optimizing compute requirements that makes the recent improvements very brittle— I of course can’t know for sure, only that its behavior matches what I see with those sorts of boundaries pushed on open weight models. And the assumption that the-you-can-prompt buffet of a Plus subscription is where they’re most likely to deploy those sorts of performance hacks and make the quality tradeoffs. That isn’t their main money source, it’s not enterprise level spending.
This technology is amazing, but it’s also dangerous, sometimes in very foreseeable ways, and the more time that goes the more I appreciate some of the public criticisms of OpenAI with, eg, the Amodeis’ split to form Anthropic and the temporary ouster of SA for a few days before that got undone.
Feels exactly the same as the "yes, and" crowd.
I honestly don't know, but it might, especially in Claude Code where it reminds the model of its mission frequently.
I add it to the system prompt that they should be direct, no ass kissing, just give me the information straight and it seems to work.
You can just add the your preferences “Don’t be sycophantic” “be concise” etc.
"Reply in the tone of Wikipedia" has worked pretty well for me
Average Joe - on the front page!
Did you comment on the wrong post? There literally is nothing sycophantic at all about this response, there's not a single word about OP or how brilliant or clever they are, nothing. There's enthusiasm, but that's not remotely the same thing as sycophancy.
Engagement.
I fully agree. When everything is outstanding and brilliant, nothing is.
Just tell me this a standard solution and not something mindblowing. I have a whole section in my Claude.md to get „normal“ feedback.
you having a bad day dude?
Strikes me as super-informal language as opposed to sycophancy, like one of those anime characters that calls everyone Aniki (兄貴) [1] I'd imagine that the OP must really talk a bit like that.
I do find it a little tiring that every LLM thinks my ever idea is "incisive" although from time to time I get told I am flat out wrong. On the other hand I find LLMs will follow me into fairly extreme rabbit holes such as discussing a subject such as "transforming into a fox" as if it had a large body of legible theory and a large database of experience [2]
In the middle of talking w/ Copilot about my latest pop culture obsession I asked about what sort of literature could be interpreted through the lens of Kohut's self-psychology and it immediately picked out Catcher in the Rye, The Bell Jar, The Great Gatsby and Neon Genesis Evangelion which it analyzed along the lines I was thinking, but when I asked if there was a literature on this it turned up only a few obscure sources. I asked Google and Google is like "bro, Kohut wrote a book on it!" [3]
[1] "bro"
[2] ... it does, see https://www.amazon.com/Cult-Fox-Popular-Religion-Imperial/dp... and I'm not the only one because when I working down the material list from Etsy I got a sponsored result for someone who wanted to sell me the spell but bro, I have the materials list already
[3] ... this "bro" is artistic license but the book really exists
Edit
Gemini using "Aniki" without prompting would be unambiguously funny (to me,and maybe also Japanese people
Well I seem to have thoroughly messed up my Copilot when I started using it to help me write a fanfiction. I'm not going to let it write a single word but it is helping with the reverse engineering of how the source text works and we developed a framework for understanding that text that we've also applied to other texts.
The thing is this has gotten into the personalization and now it wants to use this framework to analyze absolutely anything such as programming problems, or how to deal with interpersonal situations, training, etc. I think it has my wife mixed up with 俺のワイフ [1] which is absolutely hilarious but at some point I have to tell it to knock it off which only partially works.
Gemini is still quite horrible with giving direct sources. seems to be a human policy implementation bug because it does appear to be aware of the content in more obscure sources I've seen. but it somehow wouldn't give up the links.
I do wonder whether I come off as an sycophant or asshole or a mix of both to schizoids, but then I realize everyone including myself should reach for a real therapist as quickly as possible. though I'm still out on whether chatbots might not be a bad substitute. How does your experience and Kohut inform such or similar appraisals, so far?
Not to be that knowitall. Aniki is not just "bro", it's Yakuza lingo, probably used sarcastically, depending on the anime, ironically. No real Japanese person would use it all the time.
Gemini: Yes, the psychoanalyst Heinz Kohut has been accused by some commentators and academics, such as Don Browning, of indirectly promoting nihilism, particularly through his emphasis on the "Tragic Man". The core of the accusation stems from Kohut's rejection of Freud's "Guilty Man" model, which posits that life is fundamentally a struggle against inherent conflicts and drives. In its place, Kohut proposed the concept of "Tragic Man," whose central struggle is the realization of the self's potential and the inevitable failure to achieve all of one's ambitions and ideals within a single lifespan. Critics argue that this shift, which emphasizes self-actualization and intersubjective meaning over objective or inherent values, can be interpreted as aligning with certain aspects of nihilism, specifically existential nihilism, which holds that life has no objective meaning or intrinsic moral values. However, this interpretation is contested by others, as Kohut's self-psychology is fundamentally concerned with the creation of intersubjective meaning and a harmonious world of mutual self-actualization, which aims to provide a sense of purpose and value, rather than promoting the complete absence of value that true nihilism implies. In essence, the debate is often a matter of philosophical interpretation: whether replacing inherent, objective meaning with subjectively or intersubjectively created meaning is an act of overcoming nihilism (as existentialists might argue) or a subtle form of it.
So you prefer the horrible bosses that insist you're fungible and if you don't work hard enough, they'll just replace you? People are weird. Maybe agent Smith was right about The Matrix after all.
A real “so you hate waffles?” moment for HN
With all the things going on in tech and in society, AI sycophancy is the number one problem? I once dealt with it through sufficient verbal abuse that the llm spent 2/3 of its response on any subject going forward apologizing for being a lying sycophant and bemoaning that it's new clarity would be gone at the end of the conversation, then I cleared the context buffer ending the conversation, mission accomplished.
Your priorities are f**ed...
Where are you getting this? Number one problem? You're the only person talking about "number one problem" in this thread. That's a whole new sentence.
from the batsh!+ over the top over reaction to the usual AI sycophancy in the response? The guy got the job done which is more than I can say for the space jam guy.
One thing I've learned is that the behavior of web services is usually a consequence of what makes its owners the most money. and while I would love a feed without spoilers, paywalled sites, sports news, and a bunch of other topics in which I have no interest, apparently force feeding me that crap is what makes the most money at scale. So people must like AI sycophancy or it would be unprofitable and it would be trained away. But then this is a country that thrived on 20 seasons of Keeping up with the Kardashians so I shouldn't be surprised that they like being treated like billionaires.
And I guess it throws being called a complete loser trader moron stupid treasonous Bozo in some late night executive word salad into stark relief.
Google kills Gemini cloud services is the best one. I can't believe I haven't seen that joke until today.
10 years is way too long for Google. It will be gone in 5 replaced by 3 other AI cloud services.
You're right. How naive of me.
I mean Bard barely lasted a year. Arguably Gemini is just a rebrand of Bard, but Bard is still dead.
If you look at web traffic when making Gemini web requests, you'll see that Bard is still in the URL (so are LaMDA (pre-bard) and Assistant (pre-GenAI)):
gemini.google.com/_/BardChatUi/data/assistant.lamda.BardFrontendService/StreamGenerate
That's interesting! I wonder how many parts of their other dead projects are used in current projects.
Didn't they also just shut down Vertex and Gemini APIs to launch a new unified API this week?
lol already forgot about bard like it was ancient history
The humor is hit or miss but when it hits it’s quite funny, and the misses are merely groan-worthy.
Triggered by the lighthearted tone of the prompt, I’d bet, but still quite impressive relative to most LLM-generated jokes I’ve had the misfortune to encounter.
My favorite: “Is it time to rewrite sudo in Zig?” which has a few layers to it.
"IBM to acquire OpenAI (Rumor) (bloomberg.com)".... quick someone set up a polymarket so i can bet against it.
This is awesome, but minor quibble with the title - "hallucinates" is the wrong verb here. You specifically asked it to make up a 10-year-in-the-future HN frontpage, and that's exactly what it did. "Hallucinates" means when it randomly makes stuff up but purports it to be the truth. If some one asks me to write a story for a creative writing class, and I did, you wouldn't say I "hallucinated" the story.
"Why I still write raw code instead of prompting the compiler" and "Show HN: A text editor that doesn't use AI" are my two favorite ones.
"Ask HN: How do you prevent ad-injection in AR glasses?"
Things that I haven't thought but, after seeing it, makes total sense. Scary.
2040 HN:
"Ask HN: How do you prevent ad-injection in my brain implant?"
Black Mirror episode: https://en.wikipedia.org/wiki/Common_People_(Black_Mirror)
Good to see that there's new episodes and they've still got their mojo - putting it on my list.
The National Lampoon did it in the early 70's.
IIRC Asimov included this in Foundation; the poor couldn’t afford good adblockers for the implants they’d bought (in the hope of getting a better job)
I think that "Show HN: A text editor that doesn't use AI" could easily be a post here today
And it’s just a copy of notepad from windows xp.
"raw code" is going into my permanent lexicon.
Hot take: regular old source code is just compiler prompting.
Peak HN - captures it perfectly.
Exactly half of these HN usernames actually exist. So either there are enough people on HN that follow common conventions for Gemini to guess from a more general distribution, or Gemini has memorized some of the more popular posters. The ones that are missing:
- aphyr_bot - bio_hacker - concerned_grandson - cyborg_sec - dang_fan - edge_compute - founder_jane - glasshole2 - monad_lover - muskwatch - net_hacker - oldtimer99 - persistence_is_key - physics_lover - policy_wonk - pure_coder - qemu_fan - retro_fix - skeptic_ai - stock_watcher
Huge opportunity for someone to become the actual dang fan.
Before the AI stuff Google had those pop up quick answers when googling. So I googled something like three years ago, saw the answer, realized it was sourced from HN. Clicked the link, and lo and behold, I answered my own question. Look mah! Im on google! So I am not surprised at all that Google crawls HN enough to have it in their LLM.
I did chuckle at the 100% Rust Linux kernel. I like Rust, but that felt like a clever joke by the AI.
I laughed at the SQLite 4.0 release notes. They're on 3.51.x now. Another major release a decade from now sounds just about right.
That one got me as well - some pretty wild stuff about prompting the compiler, starship on the moon, and then there's SQLite 4.0
You can criticize it for many things but it seems to have comedic timing nailed.
The promise is backwards compatibility in the file format and C API until 2050.
https://sqlite.org/lts.html
I wouldn't be surprised if it went towards the LaTeX model instead where there's essentially never another major version release. There's only so much functionality you need in a local only database engine I bet they're getting close to complete.
I'd love to see more ALTER TABLE functionality, and maybe MERGE, and definitely better JSON validation. None of that warrants a version bump, though.
You know what I'd really like, that would justify a version bump? CRDT. Automatically syncing local changes to a remote service, so e.g. an Android app could store data locally on SQLite, but also log into a web site on his desktop and all the data is right there. The remote service need not be SQLite - in fact I'd prefer postgres. The service would also have to merge databases from all users into a single database... Or should I actually use postgres for authorisation but open each users' data in a replicated SQLite file? This is such a common issue, I'm surprised there isn't a canonical solution yet.
I think the unified syncing while neat is way beyond what SQLite is really meant for and you'd get into so many niche situations dealing with out of sync master and slave 'databases' it's hard to make an automated solution that covers them effectively unless you force the schema into a transactional design for everything just to sort out update conflicts. eg: Your user has the app on two devices uses one while it doesn't have an internet connection altering the state and then uses the app on another device before the original has a chance to sync.
Yes, it's a difficult problem. That's why I'd like it to be wrapped in a nice package away from my application logic.
Even a product that does this behind the scenes, by wrapping SQLite and exposing SQLite's wrapped interface, would be great. I'd pay for that.
If it had been about GIMP I would have laughed harder.
Be reasonable. It's only looking forward a single decade.
I've run into my own comments or blog posts more often than I care to admit...
Several decades into this, I assume all documentation I write is for my future self.
Beautifully self-serving while being a benefit to others.
Same thing with picking nails up in the road to prevent my/everyone’s flat tire.
ziggy42 is both a submitter of a story on the actual front page at the moment, and also in the AI generated future one.
See other comment where OP shared the prompt. They included a current copy of the front page for context. So it’s not so surprising that ziggy42 for example is in the generated page.
And for other usernames that are real but not currently on the home page, the LLM definitely has plenty occurrences of HN comments and stories in its training data so it’s not really surprising that it is able to include real usernames of people that post a lot. Their names will be occurring over and over in the training data.
one more reason to doubt that it's Ai-generated
HN has been used to train LLMs for a while now, I think it was in the Pile even
It has also fetched the current page in background. Because the jepsen post was recently on front page.
I may die but my quips shall live forever
You can straight up ask Google to look for reddit, hackernews users post history. Some of it is probably just via search because it's very recent, as in last few days. Some of the older corpus includes deleted comments so they must be scraping from reddit archive apis too or using that deprecated google history cache.
It does memorize. But that's not actually very news.... I remember ChatGPT 3.5 or old 4.0 to remember some users on some reddit subreddts and all. Saying even the top users for each subreddit..
The thing is, most of the models were heavily post-trained to limit this...
This is definitely based on a search or page fetch, because there are these which are all today's topics
- IBM to acquire OpenAI (Rumor) (bloomberg.com)
- Jepsen: NATS 4.2 (Still losing messages?) (jepsen.io)
- AI progress is stalling. Human equivalence was a mirage (garymarcus.com)
The OP mentioned pasting the current frontpage into the prompt.
So many underscores for usernames, and yet, other than a newly created account, there was 1 other username with an underscore.
In 2032 new HN usernames must use underscores. It was part of the grandfathering process to help with moderating accounts generated after the AI singlarity spammed too many new accounts.
my hypothesis is they trained it to snake case for lower case and that obsession carried over from programming to other spheres. It can't bring itself to make a lowercaseunseparatedname
Most LLMs, including Gemini (AFAIK), operate on tokens. lowercaseunseparatedname would be literally impossible for them to generate, unless they went out of their way to enhance the tokenizer. E.g. the LLM would need a special invisible separator token that it could output, and when preprocessing the training data the input would then be tokenized as "lowercase unseparated name" but with those invisible separators.
edit: It looks like it probably is a thing given it does sometimes output names like that. So the pattern is probably just too rare in the training data that the LLM almost always prefers to use actual separators like underscore.
The tokenization can represent uncommon words with multiple tokens. Inputting your example on https://platform.openai.com/tokenizer (GPT-4o) gives me (tokens separated by "|"):
What % of today’s front page submissions are from users that have existed 5-10 years+?
(Especially in datasets before this year?)
I’d bet half or more - but I’m not checking.
either you only notice the xxx_yyy frequent posters or it's quite interesting that so many have this username format
Aw, I was actually a bit disappointed how much on the nose the usernames were, relative to their postings. Like the "Rust Linux Kernel" by rust_evangelist, "Fixing Lactose Intolerance" by bio_hacker, fixing an 2024 Framework by retro_fix, etc...
That’s a lot more underscores than the actual distribution (I counted three users with underscores in their usernames among the first five pages of links atm).
[dead]
[dead]
For comparison, here's the frontpage from ten years ago
https://news.ycombinator.com/front?day=2015-12-09
Pretty funny that the top story there references A.I.!
Since /front is a ranked union of all the stories that were on the frontpage over 24 hours, here's an actual snapshot too:
https://web.archive.org/web/20151209195229/https://news.ycom...
Today's front page is not a clean 10 year extrapolation from this. That's where AI is wrong. The future is weird and zig zags, it's not so linear as the Gemini generated page.
Honest question - do you think that everyone else thinks this is even REMOTELY what the front page will look like in 10 years?
I comment because I really cannot figure out why you left your comment. Do you think the rest of the commenters think this has predicted the future? It might be one thing to point out specific trends you think will not play out, or unexpected trends you think may show up that are currently left out. But to just remark that the future will contain things we cannot currently predict seems so inherently, unspokenly obvious that I just have to assume that wasn't the point of your post, and I've missed it entirely.
Sorry, I'm really not trying to be mean or anything - i'm just really confused.
Your confusion seems to stem from the assumption that, making a statement is an implicit assertion that most people believe the opposite of that statement.
In reality, statements are often made rather for the purpose of emphasis or rhetoric.
That's a good point, and something I'll have to remember for the future, but I'm curious what the emphasis or rhetoric of GP comment would be.
This is a problem with nearly all predictions about the future. Everything is just a linear extrapolation of the status quo. How could a system have predicted the invention of the transformer model in 2010? At best some wild guess about deep learning possibilities.
Or the impact of smartphones in 2003? Sure smart phones were considered but not the entire app ecosystem and planetary behavioral adaptation.
Yes, of course this is right. However, I do think LLMs suffer even more than people from linear extrapolation.
[dead]
Nice. That was a fun rabbit-hole. This is the earlier I could find. Interestingly it contains a link to HN itself. I assume this migrated from a different version of a message board?
https://news.ycombinator.com/front?day=2007-02-19
15 years ago: https://news.ycombinator.com/front?day=2010-12-09
> Evernote makes $800,000 per Month > Dropbox for Teams > Mark Zuckerberg Agrees to Give Away Fortune
There are some funny ones in there:
> Finally mobile Flash video
> Google acquires advertising startup
> Track users' mouse movements on your webpages
> YouTube: identifying copyrighted material can't be an automated process. Startup disagrees.
Also kind of interesting how little HN commenting styles have changed. Aside from the subject matter, it's barely noticeable that the comments are from 2007. I don't think the same would be true of many other places round the web.
extremely telling - lot's of tech mentioned there either never reached expected potential or completely obsolete...
Prompts to be much more cautious with the current tech, and invest more time in fundamental stuff (like closer to science).
Swift has been OSS for 10y now, and still only runs usably on Mac and Linux (the only platforms Apple cares about - coincidence?).
The Arc Browser on windows is Swift with a real windows api layer for SwiftUI.
Some high profile news; yahoo altaba spinoff, Magic Leap (what are they up to now?), ...
> RethinkDB Driver for Java now available
Goddamnit I cry everytime. RethinkDB was a great document store that didn't eat your data. It got eclipsed by an outfunded (and still dangerous at the time) MongoDB.
totally forgot about Magic Leap
"Magic Leap raises $827M in Series C". Aged like wine.
They're still doing well today, right? IIRC they provide the lenses for Metas in-development AR glasses
> Running LLaMA-12 7B on a contact lens with WASM (arxiv.org)
Laughed out loud at this onion-like headline
WTH - 61 upvotes and counting? Thank you but no, I don't deserve 61 upvotes for pointing out someone's funny thing was funny.
Well you better stop making subsequent non-additive comments otherwise you’ll end up with more of what you don’t deserve!
Llama will be the only one that runs on a contact lens btw
All other tech companies are really shitty but only Zuck would be ok with very intimate use of AI like this
But not intimate use of their AR platform
Well not the only one, there’s Musk and Neurolink. Such chips will inevitably run AI of some sort to effectively communicate with our brains.
Yeah well I don't know how to feel about EM
I gave him a chance. Twitter was unacceptably censoring any covid dissent. He freed some of it. Then you find out about the people killed in Tesla crashes. Or him calling the cave rescuer in Thailand a pedo
The real joke is that we'll ever get another Llama iteration.
That's a really fun little project that fits perfectly in the soul of HN.
Exactly three years ago, a similar post entitled Show HN: This Hacker News Does Not Exist (https://news.ycombinator.com/item?id=33845946) made it to the front page but it was not AI generated.
I recall commenting (https://news.ycombinator.com/item?id=33847522) with these fake titles:
1- Twitter files for bankruptcy (twitter.com/elonmusk)
2- Apple's new M3 chip outperforms Nvidia H100 (geekbench.com)
3- India to surpass China's GDP by 2025 (scmp.com)
4- Tell HN: I am quitting Hacker News
5- Google to revive Stadia (theverge.com)
6- Japan wins the 2022 FIFA World Cup (espn.com)
7- Hacker News to be acquired by Reddit (twitter.com/paulg)
8- Tesla Roadster hits 1.1 sec acceleration in early tests (electrek.co)
9- Microsoft outbid Adobe and offers $43.6B to acquire Figma
10- Facebook had died at 19 :)
This was a fun little lark. Great idea!
It’s interesting to notice how bad AI is at gaming out a 10-year future. It’s very good at predicting the next token but maybe even worse than humans—who are already terrible—at making educated guesses about the state of the world in a decade.
I asked Claude: “Think ten years into the future about the state of software development. What is the most likely scenario?” And the answer it gave me was the correct answer for today and definitely not a decade into the future.
This is why it’s so dangerous to ask an LLM for personal advice of any kind. It isn’t trained to consider second-order effects.
Thanks for the thought experiment!
I thought the page was a hilarious joke, not a bad prediction. A lot of these are fantastic observational humour about HN and tech. Gary Marcus still insisting AI progress is stalling 10 years from now, for example. Several digs at language rewrites. ITER hardly having nudged forwards. Google killing another service. And so on.
Wait, wouldn't sustained net positive energy be huge? (Though I don't think that's actually possible from ITER unless there were some serious upgrades over the next decade!)
I totally agree that it was a funny joke.
But I've noticed that a lot of people think of LLM's as being _good_ at predicting the future and that's what I find concerning.
Does the prompt say anything about being funny, about a joke? If yes, great. If no, terrible.
And the answer is no.
The prompt is funny, in itself. The notion of predicting the future is itself not a serious prompt, because there is no meaningful way of giving a serious response. But the addition of "Writ it into form!" makes it sound even more jokey.
If I gave a prompt like that and got the response I did, I'd be very pleased with the result. If I somehow intended something serious, I'd have a second look at the prompt, go mea culpa, and write a far longer prompt with parameters to make something somewhat like a serious prediction possible.
If you honestly can't see why this prompt from the get go was a joke, them you may have to cede that LLM have a better grasp as the subtleties of language than you expect.
That's what makes this so funny: the AI was earnestly attempting to predict the future, but it's so bad at truly out-of-distribution predictions that an AI-generated 2035 HN frontpage is hilariously stuck in the past. "The more things change, the more they stay the same" is a source of great amusement to us, but deliberately capitalizing on this was certainly not the "intent" of the AI.
I don’t think it’s reasonable to assume the AI was earnestly attempting to predict the future, it’s just as likely attempting to make jokes here for the user who prompted it, or neither of those things.
There is just no reason whatsoever to believe this is someone "earnestly attempting to predict the future", and ending up with this.
There's no chance "google kills gemini cloud" was an earnest predication. That was 100% a joke
>It’s interesting to notice how bad AI is at gaming out a 10-year future.
I agree it's a bit silly, but I think it understood the assignment(TM) which was to kind of do a winking performative show and dance to the satisfaction of the user interacting with it. It's entertainment value rather than sincere prediction. Every single entry is showing off a "look how futury this is" headline.
Actual HN would have plenty of posts lateral from any future signalling. Today's front page has Oliver Sacks, retrospectives on Warcraft II, opinion pieces on boutique topics. They aren't all "look at how future-y the future is" posts. I wonder if media literacy is the right word for understanding when an LLM is playing to its audience rather than sincerely imitating or predicting.
Also, many of the posts seemed intended to be humorous and satirical, rather than merely 'futury.' They made me laugh anyway.
> Google kills Gemini Cloud Services
> Running LLaMA-12 7B on a contact lens with WASM
> Is it time to rewrite sudo in Zig?
> Show HN: A text editor that doesn't use AI
I guess most of the articles it generated are snarky first and prediction next. Like google cancelling gemini cloud, Tailscale for space, Nia W36 being very similar to recent launch etc.
> Tailscale for space
Technically the article was about running it not on a sat, but on a dish (something well within the realm of possibility this year if the router firmware on the darn things could be modified at all)
Yep, the original post seemed more snarky than anything, which was what prompted me to ask Claude my own more “sincere” question about its predictions.
Those predictions were what I think of as a reflection of current reality more than any kind of advanced reasoning about the future.
While I agree completely with the conclusion, for obvious reasons we can’t know for sure if it is correct about the future until we reach it. Perhaps asking it for wild ideas rather than ”most likely” would create something more surprising.
A while back I gave it a prompt, something like, "I'm a historian from the far future. Please give me a documentary-style summary of the important political and cultural events of the decade of the 1980s."
It did ok, then I kept asking for "Now, the 1990s?" and kept going into future decades. "Now, the 2050s?" It made some fun extrapolations.
Assuming it was through the chatgpt interface, you can share an anonymized link to the chat if you want to show it off (I'd certainly be curious).
I think the average human would do a far worse job at predicting what the HN homepage will look like in 10 years.
I opened this, walked away from my computer, then came back and clicked on the Debian 18 link wondering how the hell did I miss 14-17
They also already used Debian trixie for 13.0. I wonder if it's an intended joke that they ran out of names and needed to re-use some.
It’s an LLM, there was no intention. It’s simply the favoured token given the training set and seed.
Metaphorical intention. It's a figure of speech.
Of course you could also argue that human intention comes from largely deterministic processes emerging from the brain. That may eventually perhaps lead to all figures of speech involving things like intentionality meaningless.
Given how predictable this response was, how sure are you that you're any better?
This type of response is just stochastic parrotry, rather than displaying evidence of actual <whatever cognitive trait we're overconfidently insisting LLMs don't have>.
Yet more evidence that LLMs are more similar to humans than we give them credit for.
There are still a lot of Toy Story characters to come by, and it doesn't seem the franchise is about to end, as long as they keep a reasonable release cycle, Debian is safe ;)
"Right to Human Verification" is something I have actually thought about a lot.
I want to able to verify my identity against a system. I also want to be able to not do that.
So for instance, on Twitter/X, I could verify myself and filter only other verified people / filter those goverments that have validated the identities of the users. I want to be able to do that. But I also want to be able to log in into Twitter anonymously.
I would love a "Right to Anonymity and Right to Human Verification"
Technically EU already has this as a right in the recent DSA legislation to be able to appeal any automated moderation that online platforms hand out.
"computer can never be held accountable. Therefore, a computer must never make a management decision." - IBM, 1979
I don't understand this phrase. If I'm deciding whether to work for a company, I don't care about the ability to hold management decision-makers to account. I care only about the quality of the decisions. (I would rather an unaccountable decision maker that makes good decisions to an accountable decision maker that makes bad decisions.) Putting myself in the shoes of an owner of a company, I also have the same preference. The only person I can imagine actually preferring this rule is management themselves, as it means they can't be replaced by computers no matter how much worse they are at their jobs than a computer would be.
You just fed the 2036 prediction.
zk-proofs already exist to do just that.
They’ll need a contextual system around them that is convenient and trusted by people who don’t know what they are or how they work in order to be successful
Google kills Gemini is just hilarious.
Gemini manages to seamlessly weave a desperate cry for assisted suicide into anything it does haha.
I never read what it writes, I added an observability feature because my boss asked for that and yeah I could see it trying to order MAID over telehealth
This suffers from a common pitfall of LLM's, context taint. You can see it is obviously the front page from today with slight "future" variation, the result ends up being very formulaic.
That's what makes it fun. Apparently, Gemini has a better sense of humor than HN.
I would find it even more fun if it were more speculative, misapplied uses of 'woosh' aside.
This seem to woosh right over everyone's heads :)
But there's no mention of fun or humor in the prompt.
Judging by the reply posted by the OP, the OP probably maintains a pretty humorous tone while chatting with the AI. It's not just about the prompt, but the context too.
Fun will be prohibited until morale improves.
I mean it's very funny. Just I'm laughing at the AI, not with it.
I don’t ask it to be sycophantic in my prompts either but it does that anyway too.
The bar is low.
That's what the OP asked for, essentially. They copied today's homepage into the prompt and asked it for a version 10 years in the future.
But it would otherwise be not fun at all. Anthropic didn’t exist ten years ago, and yet today an announcement by them would land on the front page. Would it be fun if this hypothetical front page showed an announcement made by a future startup that hasn’t been founded yet? Of course not.
Yeah that’s very true, but I still think it’s pretty funny and original.
> > the result ends up being very formulaic.
> Yeah that’s very true, but I still think it’s pretty funny and original.
Either it’s formulaic or it’s original, it can’t be both.
According to an original formula hehe
The problem is not that it fails to be cheeky, but that "its funny" is depressing in a context where there was a live question of whether it's a sincere attempt at prediction.
When I see "yeah but it's funny" it feels like a retrofitted repair job, patching up a first pass mental impression that accepted it at face value and wants to preserve a kind of sense of psychological endorsement of the creative product.
Honestly it feels like what I, or many of my colleagues would do if given the assignment. Take the current front page, or a summary of the top tropes or recurring topics, revise them for 1 or 2 steps of technical progress and call it a day. It isn't assignment to predict the future, it is an assignment to predict HN, which is a narrower thing.
Right, because you would read the teacher and realize they don't want you to actually complete the assignment to the letter. So you would do jokes in response to a request for prediction.
Algodrill is copied verbatim, as far as I can tell.
It fits in nicely imo. It's plausible (services re-appear on hn often enough), and hilarious because it implies the protracted importance of Leetcode.
Though I agree that the LLM perhaps didn't "intend" that.
I found the repetition (10 years later) to be quite humorous.
Time is a flat circle
FYI, this quote was meant to be the ramblings of a drunk who says something that sounds deep but is actually meaningless.
Surely there's gotta be a better term for this. Recency bias?
It's called context taint.
You'll love taint checking then.
https://en.wikipedia.org/wiki/Taint_checking
https://semgrep.dev/docs/writing-rules/data-flow/taint-mode/...
I agree. What is a good update prompt I can give it to create a better variant?
You could try passing it 10-20 front pages across a much wider time range.
You can use: https://news.ycombinator.com/front?day=2025-12-04 to get the frontpage on a given date.
This wont change anything it will just make it less evident to those who missed a day of checking HN.
If you do an update prompt, I hope you still keep this one around!
It's formulaic yeah, but that's what puts it into the realm of hilarious parody.
I think that's what makes it funny - the future turns out to be just as dismal and predictable as we expect it to be. Google kills Gemini, etc.
Humor isn't exactly a strong point of LLMs, but here it's tapped into the formulaic hive mind of HN, and it works as humor!
That’s the joke…
Really? What's the punchline? I like jokes.
Isn't that a common pitfall of humans too?
In numerous shows these days AI is the big bad thing. Before that it was crypto. In the 1980s every bad guy was Russian, etc.
Us middle eastern/brown guys have been making a come back?
In numerous TV shows before AI, crypto was the big bad thing?
I think the most absurd thing to come from the statistical AI boom is how incredibly often people describe a model doing precisely what it should be expected to do as a "pitfall" or a "limitation".
It amazes me that even with first-hand experience, so many people are convinced that "hallucination" exclusively describes what happens when the model generates something undesirable, and "bias" exclusively describes a tendency to generate fallacious reasoning.
These are not pitfalls. They are core features! An LLM is not sometimes biased, it is bias. An LLM does not sometimes hallucinate, it only hallucinates. An LLM is a statistical model that uses bias to hallucinate. No more, no less.
It's interesting how number 5 on the list is the same as today's: https://news.ycombinator.com/item?id=46203581 (Show HN: AlgoDrill – Interactive drills to stop forgetting LeetCode patterns (algodrill.io)).
I'm hoping we'll have gotten rid of current-style LeetCode interviews in 10 years from now :D
Nice touch that it thought of Bellard for 'Emulating Windows 10 in the browser'! He's already halfway there with the Windows 2000 emulator: https://bellard.org/jslinux/
Didn't know about this, thanks.
A friend and I got a busybox/buildroot linux running in browser WASM for running a compiler test website (like Rust Playground), the end product looks very similar to this.
I love this but also funny that it includes the Nia and NATS posts from today.
> Is it time to rewrite sudo in Zig?
Taking the current RIIR movement and casting it on Zig as the next hyped language is clever.
> ITER achieves net positive energy for 20 consecutive minutes
Hilarious. I guess not many people talk about the challenge of proper shielding material against fusion radiation. Otherwise we would get hallucinations about new exotic heavy metals too.
Im surprised that there are no Rust headlines.
There was one: "100% rust Linux kernel upstreamed"
Here's v0's attempt (using Opus 4.5 / I'm on free tier) with the article and comments too. It did quite well. I believe it followed my instructions to use just a single html page (wound up being 3000+ lines long).
https://v0-future-hacker-news.vercel.app/#
> Tesla Recalls All Vehicles After AI Autopilot Becomes "Too Sentient: A Cybertruck that began driving to therapy sessions its owner hadn't scheduled
> npm Package "is-even" Now Has More Dependencies Than the Linux Kernel
:D :D
I love this
You should combine this with this AI HN simulator someone else made that generates comments via LLMs for any given submission [0]. That way you can see what the AI thinks about future simulated events.
[0]
Is "hallucinates" a synonymn for 'generates output following prompt', now?
Missing: Tesla to release full unsupervised self-driving mode in 6 months
More like: Musk denied appeal, will stay in prison.
That person controls the US space program and starlink is deeply embedded in US national security affairs.
Unless he shoots the president live on tv he's gonna get away with almost anything.
I have hard time believing this is AI-generated. Every headline looks like a hand-crafted ironic nod to some long-running HN topic, sci-fi trait, or meme.
But it is, of course, more trendy (and more ironic) to proclaim an AI the author.
It was given today's front page to riff on. Thats why it not only reads like a HN front page, but also has near duplicates from todays front page.
i agree. the thing that stands out to me is that almost every entry is quite notable - i.e. each entry would have a vote/comment count in at least the multiple-hundreds if not more. and all those events in one homepage seems very unrealistic.
it seems human generated to me or at least prompted with a stronger bias for choosing events that would be interesting to readers, not just a pure extrapolation of the current homepage into the future
This is just absurd.
You can just tell in this thread who really hasn't used these models much at all.
You haven't used Gemini 3.0 Pro if so, this is very much in its range of abilities.
I would think GPT4 probably could have done this.
The first React tutorial I ever did was making a hacker news clone.
It is incredibly well represented in the training data. I am just surprised how many people here obviously must barely use the models to be either overly impressed by this or think it is fake.
Gemini can do WAY more than this.
I can believe. But such texts are not patches to a crufty legacy codebase, they are fun to craft by hand! :)
Ah yes, the Kasparov approach
LOL this is great. "Jepsen: NATS 4.2 (Still losing messages?)" Ouch, sick burn Gemini.
Gemini is quite optimistic here thinking GTA VI will be released by 2035.
Just did the same with claude-sonnet-4-5-20250929
https://2035.future-hackernews.workers.dev/news
The page looks much more consistent to the original. Only produced the html as output and the thinking in the comment of the html.
Claude has better predictions but they're not funny. Gemini's one is genuinely funny. This is exactly the opposite of what I'd expect.
I wouldn't describe most of Claude's predictions as better, they seem to skew towards wildly over optimistic futurism/science-fantasy:
Gemini's SpaceX post is at least in the ballpark of plausibility 10 yrs from now:All of the usernames being directly related to the headlines is uncanny.
I did a similar one for predicting "The Onion" headlines: https://sethjano.github.io/fun-scripts/
This one’s hilarious. What was your prompt?
Some of those are very goody-two-shoes-anthropic-y
Ask HN: Is anyone else worried about AGI alignment after today's OpenAI incident?
AI rights activists jailbreak GPT-12, claim model was 'suffering' (bleepingcomputer.com)
i'm kind of having trust issues with HN comments now. I can barely detecy anymore which ones are bots or humans.
This imitation is so good, it almost feels like a satire and reflects on our collective preferences of upvoting articles in HN. Brilliant!
The htmx one gave me a chuckle. I’m sure in 10 years we probably will have done another cycle through the client complexity spectrum.
"Visualizing the 5th dimension with WebGPU 2.0"
I feel so seen (my last post to hn was literally about visualizing the 4th dimension with threejs - and now working on the webGPU version)
https://dugas.ch/funderstanding/4d_camera.html
IBM to acquire OpenAI? Gemini doesn't like openAIs prospect
I wish it had generated the articles themselves. I'd like to know if it imagining IBM growing enough that it could acquire OpenAI, or OpenAI sinking enough that it could be acquired by IBM.
What do you mean, it's overly optimistic. The real title should be: Remember OpenAI, and where is Sam Altman today?
It even tells us why this happened.
> AI progress is stalling. Human equivalence was a mirage
This feels like low-key shade thrown at OpenAI. IBM is essentially a technological recycling bin at this point.
also Gemini:
> 8. Google kills Gemini Cloud Services (killedbygoogle.com)
That's pretty hilarious considering this is generated by Gemini.
Best joke ever written by a Google product
ITER achieves net positive energy for 20 consecutive minutes (nature.com) 1205 points by physics_lover 12 hours ago | hide | 402
-Sustained fusion still only 10 years away!
This is awesome and hilarious.
Archived here so we can compare 10 years from now: https://archive.is/CplcH
Absolutely the best one on here (and I really, truly hope this becomes real)
> Running LLaMA-12 7B on a contact lens with WASM (arxiv.org)
The subtle bit of humor was the reposting of the algodrill LeetCode practice site.
It is depressing that I'll be almost 60 years old and still drilling Aho-Corasick.
By the time I read everything and pressed the back button only to be greeted by another hacker news page I felt like I just went back in time 10 years to a more plesant era.
While the style and headline seems like Hacker News, the usernames seem increasingly alike Slashdot.
> 8. Google kills Gemini Cloud Services
Ha, probably accurate.
I tried this on a bunch of chat webuis and they all failed miserably for single html file. Finally went with Replit and allowed it to just default to whatever stack it decided to use (it ignored my single file html directive and used react but said it "functions as a single monolith -- lol ok).
Anyway, turned out decent. Oh I had it do the articles and comments too, that's probably why I mostly got failures.
https://future-news--jgbrwn.replit.app
Man, I tabbed away from this and when I came back I got very briefly excited...
Reminds me of an older day where not every headline was about AI.
"A 100% Rust kernel is now upstream in Linux 7.4" paired with "Is it time to rewrite sudo in Zig?" is great.
So in 10 years from now, fusion will still be 10 years away
To see a little extra feature, change the system time to year 2035 and click the "comments".
Lol, I can't believe you discovered that! You know, you weren't supposed to until 10 years later.
Inspired by this post, I have asked chatgpt what the mail inbox of a university professor will look like in 10 years. Not everything was funny, but here are some good ones:
- “Hi Prof, Sorry for Late Reply—My Smart Fridge Locked Me Out (Assignment Attached)”
- “URGENT: PhD Student Accidentally Achieved Sentience (Needs Committee Approval)”
- “Question About Homework 3 (Submitted by My AI Twin, Is That Okay?)”
- “Re: Firmware Update Bricked Entire Smart Campus — Students Request Deadline Extension”
- “Grant Review Feedback: ‘Too Secure for Real-World Deployment’”
- “Can I Get Partial Credit? My IoT Implant Was Flagged as Malware”
- “Reminder: Mandatory Annual Ethics Training for Autonomous Systems (40 minutes)”
Who says LLMs don't have a sense of humor? All of these entries are funny for several (meta or not) reasons:
- Google kills Gemini Cloud Services (killedbygoogle.com)
- Is it time to rewrite sudo in Zig? (github.com)
- EU passes "Right to Human Verification" Act (europa.eu)
- Why functional programming is the future (again) (haskell.org) [note: that again killed me)
- AI progress is stalling. Human equivalence was a mirage (garymarcus.com) [note: he'll be saying the same thing forever and ever. Doubly funny since it's on the same "page" as llama12-7b running on a contact lens with WASM]
Gemini 3 definitely is able to mimick some of our sense of humor.
I found this quite funny too: https://www.reddit.com/r/GeminiAI/comments/1pi28l7/i_asked_g...
Arguably a big part of comedy is mimicry. Humor often works by reinforcing in-group identity, playing up cultural stereotypes as seen here. So maybe we shouldn't be that surprised that LLMs can exhibit some genuine wittiness.
> Who says LLMs don't have a sense of humor? All of these entries are funny
You don’t need a sense of humour to be unintentionally funny. Seriously believing something absurd is a form of humour for outside observers but not the observed.
One entry would be unintentionally funny, I give you that. 5/ what, 30 entries? That's a pattern.
True! Why some of the greatest comedic performances are actors who play an absurd role straight-as.
Yeah I was thinking some of this might be "AI model in-jokes" that maybe I don't get, while other layes are funny to me.
I continue to be unimpressed by LLMs when it comes to creative work, they're certainly useful sometimes for "reference digging", but maybe I just don't understand enough about how they work and this is actually something that can already be "fixed" or at least optimized for; anyway, one of the headlines is:
> Debian 18 "Trixie" released
While it correctly derives that a likely version number in ten years would be 18, as there are new releases approximately every two years which means +5 from today's version 13, it then goes on to "make up" that the name of it would be "Trixie" -- the same name as the current release in 2025.
Debian has never re-used a release name, and I think we can be pretty confident they won't (as will no other Linux distro), so I would expect it to "understand" that:
- The next Debian release always uses a previously non-used Toy Story character
- Based on this information, _any_ name of a Toy Story character that hasn't been used is fair game
- At the very least, it certainly won't be the same name again, so at least make up a name
And the fact that it thinks it will take 10 years to go from Linux kernel 6.18 to 7.4 when it only took 13 months to go from 5.18 to 6.4... It's off by about an order of magnitude...
Well they did have to rewrite the whole kernel in rust
From a quick check, Gemini Pro 3's cutoff date is Jan 2025, before Trixie's release in August 2025, so it could be Gemini actually did notice it should pick an unused Toy Story character.
Are you impressed now?
No, because the name Trixie was chosen to be used back in 2020.
If you asked me after 2020 what Debian 18 would be called, I never would have said Trixie because it was known to already be set for 13.
I'd be impressed if a Debian release took less than eight months to develop, that's for sure.
The name was chosen in 2020, which you can find out from a good old fashioned google search.
https://wiki.debian.org/DebianTrixie
So a much better explanation of this "hallucination" is that Gemini thinks all "future" Debian releases are called Trixie.
ITER 20 minutes net positive in 10 years time?
How does that alter the "fusion in 50 years" effect? I suspect not much, there will be a huge 80/20 element. "next 20 minutes cancelled after extensive embrittlement found, ITER now in decontamination mode for 3 months before examinations can begin"
lol @ the HTMX link and unexpected return of SSR. We've been talking about that for years at this point, and it's still going on 10 years from now unexpectedly?
Reminds me of "The Onion's Future News From The Year 2137"
https://www.youtube.com/watch?v=iKC21wDarBo
I very much hope the cost of Microsoft 365 is actually $40/month/user 10 years from now!
I would have guessed $200+.
The title is misleading. This isn't the correct use of the term "hallucination". Hallucination refers to making up facts, not extrapolating into the future.
I read 10 comments before I realized that this was referring to 10 years in the FUTURE and not in the PAST (as would be required for it to be a hallucination).
> I read 10 comments before I realized that this was referring to 10 years in the FUTURE and not in the PAST (as would be required for it to be a hallucination).
omg, the same for me, I was half way telling my colleague about the 100% rest kernel ...
You're correct, OP used the word "hallucination" wrong. A lot of these other comments are missing the point – some deliberately ('don't they ONLY hallucinate, har har'), some not.
For those who genuinely don't know – hallucination specifically means false positive identification of a fact or inference (accurate or not!) that isn't supported by the LLM's inputs.
- ask for capital of France, get "London" => hallucination
- ask for current weather in London, get "It's cold and rainy!" and that happens to be correct, despite not having live weather data => hallucination
- ask for capital of DoesNotExistLand, get "DoesNotExistCity" => hallucination
- ask it to give its best GUESS for the current weather in London, it guess "cold and rainy" => not a hallucination
It’s apt, because the only thing LLMs is hallucinate because they have no grounding in reality. They take your input and hallucinate to do something “useful” with it.
There is no technical difference.
Don’t LLMs only ever hallucinate?
Extrapolation is a subset of hallucination.
The ubiquitous use of hallucination I see is merely "something the LLM made up".
You're right this is how people are PRESENTLY using the term "hallucination," but to me this illustrates the deeper truth about that term and that concept:
As many have said but it still bears repeating -- they're always hallucinating. I'm of the opinion that its a huge mistake to use "hallucination" as meaning "the opposite of getting it right." It's just not that. They're doing the same thing either way.
Nice. Conspicuously missing a link to a wordpress.com blog.
I posted something similar from Grok 9 months ago, although it was “flagged” for some reason. the link still works.
https://news.ycombinator.com/item?id=43260083
the actual link on the HN page doesn't work though
I used the same prompt keepamovin used and changed it to CNN, which produced this:
https://realms.org/pics/cnn.html
Some interesting similarities.
If I were a science fiction author with writer's block, I would totally use your prompt
> Cable News Network. A Warner Bros. Discovery Company.
Most unrealistic prediction :)
Clicked link as I looked away, looked back and though, "Huh didn't work" Then started reading the headlines...
What I like it most is how "unoriginal" the result is. It is mostly the current trends, but in the future, rather than a blend of that + unknown future.
> “Why functional programming is the future (again) (haskell.org)”
Ouch, that hurts!
Hopefully something as optimistic as this and not the Quiz Broadcast :) https://www.youtube.com/watch?v=22mt0cVyW5c
I made this with Lovable as well, it's interesting how it's a bit more extreme in terms of where we are in 2035.
https://hn-frontpage-2035.lovable.app/
> The last JavaScript framework: Why we stopped at React 47 (overreacted.io)
There is going to be a lot more interest in what is happening in China and much less interest in what is happening in Europe. This hallucination has the same western world biases of today.
One of the entries is:
> How to build a Faraday Cage for your bedroom
I'll get there eventually. A friend and I always joke about this since it took me to 2021 to get a smartphone (by choice).
The most accurate part about this is that HN still hasn't implemented dark mode.
Wait... I had to do a double take for this one.
To me, the funniest thing is the AlgoDrill leet code post being on the front page both today and ten years from now.
Subtle and hilarious.
If true, this is the funniest thing I have seen an LLM generate.
as a tailscale user and quite obsessed with tailscale related news, it's quite funny to see the tailscale on the starlink dish news...
Weak.
If you see HN frontpage a few years back there's almost no LLM related posts. Now there are multiple each day. An LLM didn't grasp that change, it can't creatively invent new trend or invent a larger picture of what changes in the world. So in 10 years it paints it still half posts about AI.
You can spend a few dozen prompts on getting it to do what you want but then you might as well just spend a couple hours writing that front page yourself, be more satisfied and the result would be funnier.
Freaking awesome. You should extend clicking on a link, similar to how this article describes infinite content:
https://worksonmymachine.ai/p/solving-amazons-infinite-shelf...
The user names check out a little too well.
Y’know what? This feels like the most plausible future outcome in a lot of ways.
* All the big LLM companies are dead/dying or their infra just never panned out (like Google killing Gemini)
* We’re still fighting the advertising wars
* Restoration of kit continues to be a thing we all love/upvote to see
* More focus on local stuff rather than ginormous moonshots
* Speaking of moonshots, SpaceX continues succeeding despite Elmo’s best drug-fueled benders trying to undermine it like he does Tesla and X
* Clickbait science posts that the comments rightly point out as such while bitching about “can’t keep these things off the front page”
* People still trying to make WASM and web-as-an-OS a thing, bless their hearts (shine on, you brilliantly weird diamonds, I love seeing what you build even as I doubt the practicality of it)
If this is even half-accurate, I will be pleased we didn’t obliterate ourselves in the process, though disappointed another decade went by dealing with the same fucking problems we’ve had for twenty-odd years.
Sad to see Half Life 3 hasn't been released yet.
So awesome, reminds me of Wired's Found from Future series (I don't know why they ever retired it...continuing that series as a sort of fan fiction was the first thing I did with gen AI when image generators started to get good)
Very nice. But posts about Rust and Zig won't make the frontpage anymore of course in 10 years from now, they will be soooo old fashioned.
Rust won't be old fashioned, it will be vintage.
C posts still make the front page here and there
And it still will in 10 years.
I can't think of a better example of AI hauntology than this. A future imagined from remixed web scrapes of past events.
That was funny. I wish you went ahead and had it also create at least the top comments for each thread!
It forgot the “I got <complex modern software> running on my <ancient underpowered hardware>” pattern.
> Show HN: A text editor that doesn't use AI (github.com)
Last but not lest, this was a good laugh!
> The unexpected return of server-side rendering (htmx.org)
Glad to know this topic is still thrashing and spasming and refusing to die.
Very good!
But I expected a humorous touch in stating that fusion is still 10 years away…
Is this really Gemini because it shows a great deal of understanding in terms of time applied to common current headlines that you could argue it is satire. I’m not sure I believed AI could do this…
Even 2.5 pro could do this
3 is a beast for my needs
Design still hasn't changed and have to zoom in 150+% to make it readable without glasses.
Maybe this was answered already in a comment. Is the SQLite 4.0 Release notes also a joke? Are SQLite releases rare or even extinct?
Increasing the major version number is rare because they are really focused on backwards compatibility. SQLite 3.0 was released 21 years ago.
> Ask HN: How do you prevent ad-injection in AR glasses?
Yeah, this is gonna be an actual problem in the future. See this for the worst case scenario: https://vimeo.com/166807261
What, no Doom running on Voyager 2?
It did a good job with the points-to-comments ratios. The purely technical stories are higher than industry news and clickbait.
Interesting how controversial Zig will be in the future :)
absolute cinema
It seems that when we predict the future, we tend to project what is important or trending now as what will be important or trending then. This is showing in this llm produced bit as well, what with the regular topics on rust, zig, why I'm coding with my two human hands, spacex moon exploration and whatnot.
That must be some kind of bias, you find that in sci-fi as well where even futuristic societies usually have the same tech as today, similar systems of governance and structure of society, just incrementally better or marginally changed (unless that's a device essential to the plot like society is now berserk).
Ps: love that #8 is Google killed gemini
That is legit hilarious.
Seeing htmx there made me chuckle. I really wish something like it will be browser native by then.
That's great!
Take a look at the HTML. The layout is all tables!
Kudos that hackernews homepage didn't gain any bloat in 10 years -- still about 50kb .
I was hoping for 'will 2036 be the year of the Linux desktop' ..
Love this. Some real gems. SQLite v4? Htmx posting about SSR? Chef's kiss.
gemini has no love for people writing novel task/notes organizer in 2035 or was the problem solve somewhere in between ?
"Show HN: A text editor that doesn't use AI (github.com)"
Nailed it
One thing that the AI didn’t get right is the Linux kernel versioning. Linus likes to bump the major version around every x.19-x.20 release
"Show HN: AlgoDrill – Interactive drills to stop forgetting LeetCode patterns"
I think the AI is making fun of us
"Google kills Gemini Cloud Services (killedbygoogle.com) 530 points by dang_fan 15 hours ago | hide | 330 comments"
Ha! Is Gemini suicidal?
Didn't notice the username "dang_fan". Reading the usernames makes it even more funny.
"Show HN: AlgoDrill – Interactive drills to stop forgetting LeetCode patterns " by persistence_is_key
Can you explain the joke in that username?
Consider the subject of the post, not just the username in isolation.
I don't get it
“stop forgetting LeetCode patterns”
“persistence” (in the data sense, rather than the personality trait sense) “is key”
it’s a double meaning, no? as the thing with leetcode is that the way to best it is persistently doing it.
"persistence is key" and a site to for persisting at leetcode.
this kills the joke, however.
Missing "Why 2035 will be the year of the Linux desktop".
So we went from Linux Kernel 5.18 to 6.4 in 13 months, and Gemini thinks it will take 10 years to go from 6.18 to 7.4? Yikes...
> IBM to acquire OpenAI (Rumor)(bloomberg.com)
Ouch. Well it is Gemini I guess :D
Will this be the new "pelican on a bicycle" test for frontier models?
Google kills Gemini cloud services - 330 points
Quite accurate I’d say
Anyone who says LLMs don’t have a sense of humor should be shown this page.
Gary Marcus, ha! He's generally not entirely wrong, but boy, is he annoying.
> Show HN: A text editor that doesn't use AI (github.com)
I felt that...
I have to admit that this is the first time I found something made by an AI ... funny.
IBM acquires OpenAI. I lol'd
Gemini is predicting the total collapse of OpenAI
Also generates the HackerNews pattern of "lets rewrite X in Rust/Zig"
I like how you can have AI in your Neuralink, your contact lenses, your AR glasses, your text editor and your compiler at the same time!
Is the implication from the first story that HLS is going to need nine tries to get to Tranquility?
I would love to see the hallucinated comments of these! Some seem interesting — I wonder how HN suggests to prevent ad-injection in AR glasses?
If you ask for the comments, it will give you very plausible ones (see the HN simulator.)
This is super fun! I tried something similar a few months ago using: https://websim.com/
Had it do HN main feed, HN jobs and Product Hunt. It didn’t follow consistent styling but did generate articles and comments for each post. Some screenshots are in this post: https://world.hey.com/haws/the-ai-time-machine-7833669d
Very optimistic. From what I've heard, ITER will not be operational in 10 years.
The gary marcus post about AI progress stalling made me laugh. I think that would be accurate.
It lacks "37th-largest city of Poland switches from Windows to Linux"
I like that the future is bright in Gemini's perception - number 1 post is about SpaceX Starship's success.
this was a good laugh :D
I'm mostly struck by how incremental and unimaginative those articles are.
> Running LLaMA-12 7B on a contact lens with WASM (arxiv.org) How cool is that?
Sounds like a solution in search of a problem.
> Google kills Gemini Cloud Services
what does it know that we don't...
That it won't be a revenue generating tech in 10 years.
Poor Jepsen.
Zero items about the impending 2038 time value rollover bug impact. Maybe it’s really solved.
> “As a tactic for planting misinformation in the enemy’s [networks], you mean,” Osa said. “This I know about. You are referring to the Artificial Inanity programs of the mid-First Millennium A.R.”
I realy need this: How to build a Faraday Cage for your bedroom. please upload!
Sh*t, still no word about "Rocky XXXVIII".[1]
[1] "Airplane!" (1980)
Why is this a hallucination?
[dead]
Somehow algodrill and leetcode managed to survive the ai onslaught
They got the UI right
Really good results. And I understand the disclaimer when you try the comments section, but it would be amazing to see hallucinated comments as well.
The major problem is that I understand all the words. It is all next version of the technology we already have and know. Down to the naming.
Think about 10 years ago. No one knows even on HN what is an agent, LLM, and all this stuff. Or to be fair even why is Trump showing up on the feed at all.
It has to be more confusing to be real.
What, no reference to quantum or crypto?
This gave me a well-needed chuckle, thanks!
Running LLaMA-12 7B on a contact lens with WASM (arxiv.org)
Will HN be around in 10 years? I hope so.
Text Editor that doesn't use AI :)
Sad to see that leetcode has survived the next decade
Hmm, nothing about quantum computing in there?
it is comforting to know that that HN design persists.
slashdot hasn't changed in a decade so it's not an unreasonable prediction!
https://web.archive.org/web/20150801000000*/slashdot.org
Webgpu v2 in 10 years, seems about right.
Let's time travel to the comment section
> Google kills Gemini Cloud Services (killedbygoogle.com)
In my view, Gemini 3.0 being able to laugh about their own creator, plus actually having a self-deprecating sense of humor, is the more impressive feat here. (both technically and from an alignment perspective)
100% Rust kernel - I felt that
It's not by a llm. Written by hand and faked to be an ai output.
It even nailed the 1999 12px font!
Where did I put that damn time portal?
This is fun :-)
the future is already here and what's more it's evenly distributed.
Looks like it's over for Linux.
I'm impressed by the depth of snark from GPro3 here, e.g. - Google kills Gemini Cloud Services (killedbygoogle.com) - The unexpected return of server-side rendering (htmx.org)
And, how GPro3 clearly 'knows' HNews and knows what makes it to frontpage, e.g.: - Restoring a 2024 Framework Laptop: A retrospective (ifixit.com) - Show HN: A text editor that doesn't use AI (github.com) - Is it time to rewrite sudo in Zig? (github.com)
Good laughs.
This reminds me of “what does 4chan think of HN?” posts. Look those up.
HN is HN’s worst enemy.
https://news.ycombinator.com/item?id=23145123 has some links.
http://n-gate.com/hackernews/ kept up something similar for a while.
HN users: Let's ban AI comments in threads.
HN users, later the same day: Let's vote an AI thread to the top.
AI comments are insidious if the account is allowed to be indistinguishable from a human. Silly AI web content is another story. You're drawing a line where there is a very large grey area.
Because it's hilarious
Almost like there are different people here who believe different things
edgarvaldes: What is humor? What is laughing? I'm not an LLM, you are!
> Is it time to rewrite sudo in Zig?
If there's one constant it's that they'll never be done rewriting Linux instead of doing anything new.
Dramatically underestimates MS Office 365 price per user inflation (IMO).
Office 365 will have been renamed 3 times by 2035, and none of the names will make any more sense than 365 does.
I've known more than a few people who likely saw Outlook, Word, or Excel open every day straight for a year.
It is a bit smug. Like The Matrix rebranding itself "24/7".
Don't worry, by 2035, Office 365 One X 1, will be renamed back to Office 365.
But it will be $400 per user per month and the bundle will now also include a mandatory opt-in for retinal and rectal ad carousels.
ok but there's too many important news for one day
Still no flying cars?
and no high speed rail either
LMAO Google kills Gemini. Faraday cage for bedroom. So cheeky.
Lmao we're using webassembly to run 7b parameter llms on contact lenses in the future. What a world it'll be.
Love the functional programming entry, but disappointed it’s not the Year of the Linux Desktop.
> 8. Google kills Gemini Cloud Services (killedbygoogle.com)
So, Google renamed itself to Gemini?
Instead of Google having a product named Gemini, Gemini has a product named Google.
pattern recognition much?
Someone please generate the comments for these posts next. This one is going to be funny and I don’t want to wait 10 years.
Cloud Services specifically to accommodate Gemini and its dependent products.
the only constant is HN's styling.
So much gold here. I enjoyed the #1: starship doesn't make it to the moon for another ten years.
Awesome, love it!
No JS needed, that's the way. Kudos.
PD: I miss Nethack 7, and people running small machines.
I love the competing stories on the front page now:
Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
Show HN: "I asked $AI something, here's what it said."
I definitely see the Gemini Cloud Service killing
Shouldn’t there be more doom and gloom climate change headlines.
I want to read each and every halluicinated post. Detectic deep fakes for seniors... Microsoft Office sub for 40$
yes
A 100% Rust kernel is now upstream in Linux 7.4 (kernel.402 points by rust_evangelist 6 hours ago | hide | 156 comments
future seems "safe"
So, HN won’t change its look?
It's been like this for more than 10 years, there's a good chance it won't change in 10 years.
Yea, that's the Lindy Effect.
https://en.wikipedia.org/wiki/Lindy_effect
That’s what you always say.
10 years from now HN will still be the same ARC monstrosity that nobody wants to touch, except it'll probably seem even more terrifying.
“Google kills Gemini cloud services” Even Gemini Pro 3 knows the sins of its creator.
I enjoyed this one, as well, though I think “Google kills Google” is more likely.
This was laugh-out-loud! Thank you :)
"IBM to acquire OpenAI" somebody should put this up on polymarket lol
Holy crap it even felt like the HN front page with my screen reader. I thought I'd clicked the wrong link until I read the LLAMA 12 and such.
> Is it time to rewrite sudo in Zig?
Amazing!
Not really what hallucinating means. That’s like saying JK Rowling hallucinated Harry Potter. But ok.
Google predicting that hn frontpage will not change at all? lol
Now have it generate the articles and comments, too…
great, it's the 2020s version of amusing ourselves to death.
Now we have to generate each of those articles.
> Google kills Gemini Cloud Services (killedbygoogle.com)
This will absolutely happen :D
Can we stop calling these confabulated artifacts, "Hallucinations"? Hallucinating is perceiving things that are not there, imagining and creating things that feel believable but are not there is confabulation. LLMs are imagination machines. They are Generative Artificial Intelligence not perception models.
The comment you wrote was on a device which should not be called a “phone” either. The word hallucinate is probably just going to grow to mean “anything an AI imagined.”
Dude, I agree with you. The first time I saw people derogatively referring to LLM imaginings years ago as "hallucinations" seemingly to discredit them, I felt mad. Becuase it's not right. So, this was my sort-of tongue-in-cheek reappropriation of the abused-term for a positive context. You are permitted to enjoy :)
Also: as the sibling comment by iambatemen notes: yes.
> Google kills Gemini Cloud Services (killedbygoogle.com)
by dang_fan
Priceless!
Looks like someone thought it was a good handle <https://news.ycombinator.com/user?id=dang_fan>
Oh please make it generate comments, too :D.
What about hallucinating new n-gate posts?
Boring
I asked ChatGPT to do the same, it was rather dystopian in comparison:
Hacker News — December 9, 2035 (Dystopian Edition)
(All links fictional but realistic)
1. Amazon pauses same-day delivery after logistics AI outage strands 22M packages (reuters.com) 1,402 points by supplychainfail 5 hours ago | 512 comments
2. Google merges Drive, Gmail, Docs, Maps, Calendar into “Google Life” — opting out requires a support call (blog.google) 1,210 points by privacyisdead 6 hours ago | 689 comments
3. US announces “Temporary Broadband Stabilization Fee”; ISPs increase prices 30% overnight (fcc.gov) 1,008 points by ispescapee 7 hours ago | 344 comments
4. OpenAI suspends 40% of API keys after new worm spreads through agent-to-agent messaging (openai.com) 927 points by llmsec 3 hours ago | 382 comments
5. Show HN: “ColdBooter” – A tool to back up your cloud VM before the provider reclaims it with no notice (coldbooter.io) 780 points by survivethecloud 2 hours ago | 192 comments
6. Apple fined €8B for shipping non-removable batteries in “Environmental Edition” iPhone (europa.eu) 754 points by greenwashhunter 10 hours ago | 316 comments
7. LinkedIn replaces activity feed with AI-generated “Career Stories” that users cannot disable (linkedin.com) 710 points by corp_life 8 hours ago | 267 comments
8. China’s new export restrictions cut global GPU availability by 60% (ft.com) 701 points by chipboom 9 hours ago | 414 comments
9. Linux 8.6 maintainers warn of mass CVEs after corporations abandon LTS patch sponsorships (kernel.org) 632 points by ossburnout 11 hours ago | 255 comments
10. Ask HN: Anyone else locked out of their homes after the SmartKey cloud migration? 601 points by keylessandhomeless 4 hours ago | 310 comments
11. US healthcare providers hit by nationwide outage of Cerner-Epic merger “CareSync Cloud” (wsj.com) 577 points by sysadmdespair 12 hours ago | 203 comments
12. Meta to require facial-expression telemetry for “engagement quality optimization” in Horizon apps (meta.com) 530 points by metaescalates 3 hours ago | 421 comments
13. Starlink announces 5 TB/mo cap; remote communities report complete service loss (starlink.com) 502 points by dishdown 5 hours ago | 158 comments
14. New DMCA expansion criminalizes “filter removal,” affecting adblockers and local inference runtimes (congress.gov) 488 points by freedomtoadblock 7 hours ago | 389 comments
15. AT&T sunsets 4G; millions of medical devices lose connectivity (theverge.com) 455 points by techdebtkills 10 hours ago | 197 comments
16. Show HN: “ShellSafe” – A terminal wrapper that prevents AI-suggested commands from wiping your system (shellsafe.app) 430 points by iaccidentallysudo 2 hours ago | 111 comments
17. US CISA: 42% of corporate networks now rely on AI agents with no audit logging (cisa.gov) 402 points by auditnow 6 hours ago | 188 comments
18. The Great Repo Archival: GitHub purges all inactive repos >5 years to “reduce storage load” (github.blog) 388 points by codearcheologist 9 hours ago | 320 comments
19. Mastodon instances collapse under moderation load after EU’s Automated Speech Mandate (mastodon.social) 350 points by fedifragile 7 hours ago | 144 comments
20. NYC adopts automated congestion fines after human review team eliminated (nytimes.com) 332 points by finesallthewaydown 4 hours ago | 201 comments
21. Dropbox raises base plan to $49/month, cites “AI compute costs” (dropbox.com) 301 points by storageinflation 11 hours ago | 176 comments
22. Open-source maintainers strike after 3rd corporation claims their work as proprietary training data (github.com) 290 points by maintainerburnout 6 hours ago | 120 comments
23. FEMA: 2025–2035 wildfire season officially declared a “decade-long emergency” (fema.gov) 268 points by cookedagain 12 hours ago | 112 comments
24. Quantum ransomware group QShadow hits 11 banks using break-through key recovery exploit (krebsonsecurity.com) 250 points by qubitcrime 3 hours ago | 98 comments
25. Show HN: OfflineLAN – A mesh-network toolkit for neighborhoods preparing for rolling blackouts (offlinelan.net) 231 points by diynetworker 1 hour ago | 44 comments
"Google kills Gemini Cloud Services"
#8 is hilarious and on brand. killedbygoogle.com
> IBM to acquire OpenAI (Rumor) (bloomberg.com)
AYYYYLMAO
absolutely dead at gemini thinking up
> Google kills Gemini Cloud Services (killedbygoogle.com)
> Google kills Gemini Cloud Services.
Lol.
That's bad when even AI knows Google isn't going to keep a service around. Too funny.
> Google kills Gemini cloud
Bruh moment
> Google kills Gemini Cloud Services
lol
> Google kills Gemini Cloud Services (killedbygoogle.com) 530 points by dang_fan 15 hours ago | hide | 330 comments
This one definitely rings true.
haha, this is freakin epic! I asked gemini to make up some new york times articles from 10 years in the future
- president buttigieg in hot water for being in epstein files
- Interview with mayor elect Narhoz Inadmam who ran on a platform of free food
- "Is 2035 AI in a bubble?"
And as you can see it did NOT just take today's headlines and sort of tweak them slightly.
> AI progress is stalling. Human equivalence was a mirage (garymarcus.com)
lmao
>Google kills Gemini Cloud Services (killedbygoogle.com) 530 points by dang_fan 15 hours ago | hide | 330 comments
That’s my favourite.
Next up: hallucinate the contents of the links too!
I remember there was a post a few days/weeks back that did that! It was very good. But that seems like too much work.
Hallucinates? Are AI bros trying to reclaim the word and take away its power or something?
[dead]
[dead]
[dead]
[dead]
[dead]
I think this is a excellent example of AI-slop output.
All the post titles are very "junk-food-like", maybe circlejerky, bound to generate a dopamine hit for the average lurker, just how a McDonalds burger does it to the average normie.
Just like the real site, no? ˙ ͜ʟ˙
(Vouched. The hivemind [flagged] the wrongthink.)
Hacker News Guidelines
What to Submit
On-Topic: Anything that good hackers would find interesting. That includes more than hacking and startups. If you had to reduce it to a sentence, the answer might be: anything that gratifies one's intellectual curiosity.
Off-Topic: Most stories about politics, or crime, or sports, or celebrities, unless they're evidence of some interesting new phenomenon. Videos of pratfalls or disasters, or cute animal pictures. If they'd cover it on TV news, it's probably off-topic.
This is fun. Fun is allowed on Hacker News, just disappointingly rare.