Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 3

blog.google

Post reply on HN
Print view View original

771–780 of 1001 posts

Re: Gemini 3

#771

Post by SchemaLoad »

echelon wrote: post #327
bigstrat2003 wrote: post #317

Earlier quoted context omitted.

No LLM has ever been as good as people said it was. That doesn't mean this one won't be, but it does make it an unlikely bet based on past trends.

There are 8 Google news articles in the top 15 articles on the HN front page right now. Google being able to skip ahead of every other AI company is wild. They just sat back and watched, then decided it was time to body the competition. The DOJ really should break up Google [1]. They have too many incumbent advantages that were already abuse of monopoly power. [1] https://pluralpolicy.com/find-your-legislator/ - call…

Google didn't sit back and watch, they basically built the whole foundations for all of this. They were just not the first ones to release a chatbot interface.

Re: Gemini 3

#772

Post by legel »

panarky wrote: post #697
lairv wrote: post #293

Out of curiosity, I gave it the latest project euler problem published on 11/16/2025, very likely out of the training data Gemini thought for 5m10s before giving me a python snippet that produced the correct answer. The leaderboard says that the 3 fastest human to solve this problem took 14min, 20min and 1h14min respectively Even thought I expect this sort of problem to very much be in the distribution of what the mo…

[flagged]

Thanks for reporting these metrics and drawing the conclusion of an underlying breakthrough in search.

In his Nobel Prize winning speech, Demis Hassabis ends by discussing how he sees all of intelligence as a big tree-like search process.

https://youtube.com/watch?v=YtPaZsasmNA&t=1218

Re: Gemini 3

#773

Post by SchemaLoad »

ryandrake wrote: post #447
dudeinhawaii wrote: post #355

Gemini has been so far behind agentically it's comical. I'll be giving it a shot but it has a herculean task ahead of itself. It has to not only be "good enough" but a "quantum leap forward". That said, OpenAI was in the same place earlier in the year and very quickly became the top agentic platform with GPT-5-Codex. The AI crowd is surprisingly not sticky. Coders quickly move to whatever the best model is. Excited t…

I don't even know what the fuck "agentic" is or why the hell I would want it all over my software. So tired of everything in the computing world today.

As far as I can tell, it just means giving the LLM the ability to run commands, read files, edit files, and run in a loop until some goal is achieved. Compared to chat interfaces where you just input text and get one response back.

Re: Gemini 3

#774

Post by slaterbug »

tylervigen wrote: post #577
rvnx wrote: post #47

Earlier quoted context omitted.

This is a list of questions and answers that was created by different people. The questions AND the answers are public. If the LLM manages through reasoning OR memory to repeat back the answer then they win. The scores represent the % of correct answers they recalled.

That is not entirely true. At least some of these tests (like HLE and ARC) take steps to keep the evaluation set private so that LLMs can’t just memorize the answers. You could question how well this works, but it’s not like the answers are just hanging out on the public internet.

Excuse my ignorance, how do these companies evaluate their models against the evaluation set without access to it?

Re: Gemini 3

#775

Post by jorvi »

windexh8er wrote: post #740
TechDebtDevin wrote: post #691

Earlier quoted context omitted.

Why is this sad. You should bw rooting for these LLMs to be as bad as possible..

If we've learned anything so far it's that the parlor tricks of one-shot efficacy only gets you so far. Drill into anything relatively complex with a few hundred thousand tokens of context and the models all start to fall apart roughly the same. Even when I've used Sonnet 4.5 with 1M token context the model starts to flake out and get confused with a codebase of less than 10k LoC. Everyone seems to keep claiming thes…

Same. I've been needing to update an userscript (JS) that takes stuff like "3 for the price of 1", "5 + 1 free", "35% discount!" from a particular site and then converts the price to a % discount and the price per item / 250 grams.

Its an old userscript so it is glitchy and halfway works. I already pre-chewed the work by telling Gemini 3 exactly which new HTML elements it needs to match and which contents it needs to parse. So basically, the scaffolding is already there, the sources are already there, it just needs to put everything in place.

It fails miserably and produces very convincing looking but failing code. Even letting it iterate multiple times does nothing, nor does nudging it in the correct direction. Mind you that Javascript is probably the most trained-on language together with Python, and parsing HTML is one of the most common usecases.

Another hilarious example is MPV, which has very well-documented settings. I used to think that LLMs would mean you can just tell people to ask Gemini how to configure it, but 9 out of 10 times it will hallucinate a bunch of parameters that never existed.

It gives me an extremely weird feeling when other people are cheering that it is solving problems at superhuman speeds or that it coded a way to ingest their custom XML format in record time, with relatively little prompting. It seems almost impossible that LLMs can both be so bad and so good at the same time, so what gives?

Re: Gemini 3

#777

Post by eterm »

> It seems there's a date conflict. The prompt claims it's 2025, but my internal clock says otherwise.

> I'm now zeroing in on the temporal aspect. Examining the search snippets reveals dates like "2025-10-27," suggesting a future context relative to 2024. My initial suspicion was that the system time was simply misaligned, but the consistent appearance of future dates strengthens the argument that the prompt's implied "present" is indeed 2025. I am now treating the provided timestamps as accurate for a simulated 2025. It is probable, however, that the user meant 2024.

Um, huh? It's found search results for October 2025, but this has led it to believe it's in a simulated future, not a real one?

Re: Gemini 3

#778

Post by hollowturtle »

SXX wrote: post #443
SXX wrote: post #366

Static Pelican is boring. First attempt: Generate SVG animation of following: 1 - There is High fantasy mage tower with a top window a dome 2 - Green goblin come in front of tower with a torch 3 - Grumpy old mage with beard appear in a tower window in high purple hat 4 - Mage sends fireball that burns goblin and all screen is covered in fire. Camera view must be from behind of goblin back so we basically look at towe…

After few more attempts longer animation with a story from my gamedev inspired mind: https://codepen.io/Runway/pen/zxqzPyQ PS: but yeah thats attempt #20 or something.

Wow looks like total shit and eventually very hard to take on and actually improve it, given the convoluted code it generated, YET people are impressed. What world are we living in...

Re: Gemini 3

#779

Post by zarzavat »

davidpolberger wrote: post #692

This is wild. I gave it some legacy XML describing a formula-driven calculator app, and it produced a working web app in under a minute: https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%... I spent years building a compiler that takes our custom XML format and generates an app for Android or Java Swing. Gemini pulled off the same feat in under a minute, with no explanation of the format. The XML is fairly…

This is exactly the kind of task that LLMs are good at.

They are good at transforming one format to another. They are good at boilerplate.

They are bad at deciding requirements by themselves. They are bad at original research, for example developing a new algorithm.

Re: Gemini 3

#780

Post by Taek »

dyauspitr wrote: post #273
dwringer wrote: post #236

Well, I tried a variation of a prompt I was messing with in Flash 2.5 the other day in a thread about AI-coded analog clock faces. Gemini Pro 3 Preview gave me a result far beyond what I saw with Flash 2.5, and got it right in a single shot.[0] I can't say I'm not impressed, even though it's a pretty constrained example. > Please generate an analog clock widget, synchronized to actual system time, with hands that upd…

Having seen the page the other day this is pretty incredible. Does this have the same 2000 token limit as the other page?

No, and also the other page was pure HTML and CSS. This clock is using React and Javascript, so it's not a fair comparison.
Post reply on HN