Earlier quoted context omitted.
I may live to see it; peak sqlite.
You are laughing. IBM has already been there, with DB2 having essentially been the OS on mainframes a few decades ago.
All of this has happened before. All of this will happen again.
Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
771–780 of 1001 posts
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#772Change the HN navigation to: new | threads | past | future | …
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#773Earlier quoted context omitted.
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: "SpaceX announces Mars City Alpha is now self-sustaining (spacex.com)" Show HN: I built an IDE for direct neural programming (thoughtexchange.io) Gemini's SpaceX post is at least in the ballpark of plausibility 10 yrs from now: First successful telemetry from Starship HLS-9 on the Sea…
OK, they're more realistic then. It seems to have made an actual attempt to be accurate, whereas Gemini chose satire and was surprisingly good at it.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#774Earlier 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?
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…
Comedy gold. The whole "Right to Human Verification" Act bit sound eerily plausible and realistic, but then we get this bit:
"A recent Eurobarometer survey showed that 89% of Europeans cannot tell the difference between their spouse and a well-prompted chatbot via text."
Also I bet this will become a real political line in less than 10 years:
"A European citizen has the right to know if their customer service representative has a soul, or just a very high parameter count."
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#775Prompt: 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 doesn’t sound like Gemini at all, it’s very bland and business like. Suspect your prompt contains more to ask it to be in a certain style.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#776Earlier quoted context omitted.
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…
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
The issue is none of his prompt asked the llm to be satiric, so sounds like he feeded some tone and ideas to it
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#777Prompt: 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 the best thing I've seen all month. I'm actually blown away at just how accurate it is in making up the potential front page posts.
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#778This 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.
If someone asked you, you would know about the context. LLMs are predictors, no matter the context length, they never "know" what they are doing. They simply predict tokens.
This common response is pretty uninteresting and misleading. They simply predict tokens? Oh. What does the brain do, exactly?
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#779Earlier 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?
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…
Blocked by FortiGate as pornography of all things... submitted for review, but got a chuckle out of me lol
Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now
#780Earlier quoted context omitted.
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
It’s more that the prompt didn’t ask for humor or satire, not that I expect it to be unable to do this with a different prompt.
It didn't have to, not explicitly. The tone and the context already hint at that - if you saw someone creating a fake cover of an existing periodical but 10 years into the future, you'd likely assume it's part of some joke or a commentary related to said periodical, and not a serious attempt at predicting the future. And so would an LLM.
People keep forgetting (or worse, still disbelieving) that LLMs can "read between the lines" and infer intent with good accuracy - because that's exactly what they're trained to do[0].
Also there's prior art for time-displaced HN, and it's universally been satire.
--
[0] - The goal function for LLM output is basically "feels right, makes sense in context to humans" - in fully general meaning of that statement.