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

851–860 of 1001 posts

Re: Gemini 3

#851

Post by bluecalm »

jeswin wrote: post #742
pclmulqdq wrote: post #466

Earlier quoted context omitted.

Yeah, it is often pointed out as a brilliance in game analysis if a GM makes a move that an engine says is bad and turns out to be good. However, it only happens in very specific positions.

> Yeah, it is often pointed out as a brilliance in game analysis if a GM makes a move that an engine says is bad and turns out to be good. Do you have any links? I haven't seen any such (forget GM, not even Magnus), barring the opponent making mistakes.

It used to happen way more often with Magnus and classical versions of Stockfish from pre Alpha Zero/Leela Zero days. Since NN Stockfish I don't think it happens anymore.

Re: Gemini 3

#852

Post by oblio »

Agentlien wrote: post #819
oblio wrote: post #798

Earlier quoted context omitted.

90% of writing code, sure. But most professionnel programmers write code maybe 20% of the time. A lot of the time is spent clarifying requirements and similar stuff.

The more I hear about other developers' work, the more varied it seems. I've had a few different roles, from one programmer in a huge org to lead programmer in a small team, with a few stints of technical expert in-between. For each the kind of work I do most has varied a lot, but it's never been mostly about "clarifying requirements". As a grunt worker I mostly just wrote and tested code. As a lead I spent most time…

> As a lead I spent most time

> mentoring

Clarifying either business or technical requirements for newer or junior hires.

> reviewing code

See mentoring.

> or in meetings

So clarifying requirements from/for other teams, including scope, purely financial or technical concerns, etc.

Rephrase "clarifying requirements" to "human oriented aspects of software engineering".

Plus, based on the graphics debugger part of your comment, you're a game developer (or at least adjacent). That's a different world. Most software developers are line of business developers (pharmaceutical, healthcare, automotive, etc) or generalists in big tech companies that have to navigate very complex social environments. In both places, developers that are just heads down in code tend not to do well long term.

Re: Gemini 3

#853

Post by Der_Einzige »

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]

You clearly AI generated this comment.

Re: Gemini 3

#854

Post by belter »

vitorgrs wrote: post #795
panarky wrote: post #697

Earlier quoted context omitted.

[flagged]

I usually ask a simple question that ALL the models get wrong: List of mayor of my city [Londrina]. ALL the models (offine) get wrong. And I mean, all the models. The best that I could, it's o3 I believe, saying it couldn't give a good answer for that, and told to access the city website. Gemini 3 somehow is able to give a list of mayors, including details on who got impeached, etc. This should be a simple answer, be…

I asked Claude, and had no issues with the answer including mentioning the impeached Antonio Belinati...

Re: Gemini 3

#855

Post by closewith »

int_19h wrote: post #667
closewith wrote: post #540

Earlier quoted context omitted.

So where do I get a API key? Where do I sign up for Ultra?

For API key, go to https://aistudio.google.com/ and there's a link in the bottom left. But this is if you want to pay per token. Otherwise you should just be able to use your Gemini Pro subscription (it doesn't need Ultra). Subscriptions are at https://gemini.google/subscriptions/

Okay, thanks. Unfortunately, when I try to sign up to a plan on https://gemini.google/subscriptions/, I am redirected to the Workspace Admin (as I'm a business user and One is only available to personal accounts), where I am offered Google Ultra AI for Business for €216 per month, but I can only upgrade the entire Workspace or nothing!

Is that correct? I can't even upgrade a Group separately?

Re: Gemini 3

#856

Post by versteegen »

momojo wrote: post #761
panarky wrote: post #719

Earlier quoted context omitted.

Hmmm, I wrote those words myself, maybe I've spent too much time with LLMs and now I'm talking like them?? I'd be interested in any evidence-based arguments you might have beyond attacking my writing style and insinuating bad intent. I found this commenter had sage advice about how to use HN well, I try to follow it: https://news.ycombinator.com/item?id=38944467

You mentioned "step change" twice. Maybe a once over next time? My favorite Mark Twain quote is (very paraphrased) "My apologies, had I more time, I would have written a shorter letter".

I thought the repetition was intentional.

Re: Gemini 3

#857

Post by Cthulhu_ »

codespin wrote: post #784
zarzavat wrote: post #779

Earlier quoted context omitted.

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.

> They are good at transforming one format to another. They are good at boilerplate. You just described 90% of coding

Thing is, and LLM doesn't need motivation or self-discipline to start writing, which at this point I'm confident is the main slowing down factor in software development, after requirements etc.

Re: Gemini 3

#859

Post by jmmcd »

BoorishBears wrote: post #461
jmmcd wrote: post #61

Earlier quoted context omitted.

"Pelican on bicycle" is one special case, but the problem (and the interesting point) is that with LLMs, they are always generalising. If a lab focussed specially on pelicans on bicycles, they would as a by-product improve performance on, say, tigers on rollercoasters. This is new and counter-intuitive to most ML/AI people.

The gold standard for cheating on a benchmark is SFT and ignoring memorization. That's why the standard for quickly testing for benchmark contamination has always been to switch out specifics of the task. Like replacing named concepts with nonsense words in reasoning benchmarks.

Yes. But "the gold standard" just means "the most natural, easy and dumb way".

Re: Gemini 3

#860

Post by motbus3 »

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…

We need to wait and see. According to Google they have solved AI 10 years ago with Google Duo but somehow they keep smashing records despite being the worst coding tool until Gemini 2.5. Google internal benchmarks are irrelevant
Post reply on HN