alt Hacker NewsShow HN: Gemini Pro 3 hallucinates the HN front page 10 years from now
Comments
Google kills Gemini cloud services is the best one. I can't believe I haven't seen that joke until today.
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.
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.
A text editor that doesn't use AI is pretty much what I Show-HN-ed few days ago: https://kraa.io/about
I'll wait 10 years to post it again.
For comparison, here's the frontpage from ten years ago
> Running LLaMA-12 7B on a contact lens with WASM (arxiv.org)
Laughed out loud at this onion-like headline
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 :)
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
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!
This is the most hilarious list ever. Google kills Gemini Cloud Services. This AI has quite a psycho sense of humor against itself.
A text editor that doesn't use AI, lol, that's a deep joke for an AI.
"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"
The 2 things that you can comfortably predict with good accuracy: EU passing new regulation laws & yet another YC company trying to give context to AI agents.
"Is it time to rewrite sudo in Zig?"
This is rage bait! :-)
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).
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.
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/
Oh man, that's totally worth $500 Billion dollars and the environmental health of our towns and cities!
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
*FDA approves over-the-counter CRISPR for lactose intolerance*
Finally, science has gone full Costco. Just imagine you stroll into CVS, grab a bag of Doritos, a gallon of milk, and—oh look—CRISPR in aisle 3.
‘Excuse me, where do you keep the gene-editing kits?’ ‘Right next to the chewing gum, sir.’
Now lactose intolerant folks can casually reprogram their DNA like they’re updating an iPhone.
Warning label: ‘Side effects may include glowing in the dark, mooing at strangers, and sudden urges to graze in fields.’
Honestly, I can’t wait for the sequel: over-the-counter CRISPR for people who can’t parallel park.
> 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.
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]
> A 100% Rust kernel is now upstream in Linux 7.4
the future predicted by gemini is already coming true; from 3 hours ago <https://news.ycombinator.com/item?id=46213585>:
"Rust ... is now a core part of the kernel and is here to stay"
Missing: Tesla to release full unsupervised self-driving mode in 6 months
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.
It is obvious that everything that has been dreamed up relates to what exists now. There are no examples of real creativity or anything new or unexpected. This is my worst fear for the future: that novel ideas will become less commonplace and texts will become more average.
The only good news to me is: The EU still exists.
Is "hallucinates" a synonymn for 'generates output following prompt', now?
LOL this is great. "Jepsen: NATS 4.2 (Still losing messages?)" Ouch, sick burn Gemini.
Big models keep getting better at benchmarks, but reliability under messy real world inputs still feels stuck in place.
Gemini is quite optimistic here thinking GTA VI will be released by 2035.
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.
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.
It's cute that Gemini thinks OpenAI will be around in 10 years.
IBM to acquire OpenAI? Gemini doesn't like openAIs prospect
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)
I would appreciate the same thing written by a human. That human would probably have lots of fun writing this.
> 8. Google kills Gemini Cloud Services
Ha, probably accurate.
"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)
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.
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.
> 27. The unexpected return of server-side rendering (htmx.org)
Ha this one got me
A similar project of mine (generated back when GPT-4 was out, along with comment threads and articles):
To see a little extra feature, change the system time to year 2035 and click the "comments".
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]
"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
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?
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
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: