> Show HN: A text editor that doesn't use AI (github.com)
Last but not lest, this was a good laugh!
Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
581–590 of 1001 posts
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#582Earlier quoted context omitted.
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 t…
Exactly, it fixates on a handful of comments chosen apparently randomly.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#583I 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
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#584Earlier quoted context omitted.
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?
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
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#585Wait... 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.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#586ITER 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"
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#587Earlier quoted context omitted.
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 r…
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.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#588I 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.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#589Earlier quoted context omitted.
10 years is way too long for Google. It will be gone in 5 replaced by 3 other AI cloud services.
I mean Bard barely lasted a year. Arguably Gemini is just a rebrand of Bard, but Bard is still dead.
Didn't they also just shut down Vertex and Gemini APIs to launch a new unified API this week?
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#590Prompt: Here is the front page from today: 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 creat…
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's Replit's attempt