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

Gemini 3.1 Pro

blog.google

Post reply on HN
Print view View original

261–270 of 951 posts

Re: Gemini 3.1 Pro

#261

Post by m_ke »

esafak wrote: post #17

Has anyone noticed that models are dropping ever faster, with pressure on companies to make incremental releases to claim the pole position, yet making strides on benchmarks? This is what recursive self-improvement with human support looks like.

this is mostly because RLVR is driving all of the recent gains, and you can continue improving the model by running it longer (+ adding new tasks / verifiers)

so we'll keep seeing more frequent flag planting checkpoint releases to not allow anyone to be able to claim SOTA for too long

Re: Gemini 3.1 Pro

#262

Post by nubg »

qingcharles wrote: post #25

I've been playing with the 3.1 Deep Think version of this for the last couple of weeks and it was a big step up for coding over 3.0 (which I already found very good). It's only February...

> I've been playing with the 3.1 Deep Think version of this

How?

Re: Gemini 3.1 Pro

#263

Post by mikepurvis »

enobrev wrote: post #105
embedding-shape wrote: post #73

Earlier quoted context omitted.

It's an excellent demonstration of the main issue I have with the Gemini family of models, they always go "above and beyond" to do a lot of stuff, even if I explicitly prompt against it. In this case, most of the SVG ends up consisting not just of a bike and a pelican, but clouds, a sun, a hat on the pelican and so much more. Exactly the same thing happens when you code, it's almost impossible to get Gemini to not do…

I have the same issue. Even when I ask it to do code-reviews and very explicitly tell it not to change files, it will occasionally just start "fixing" things.

I find Copilot leans the other way. It'll myopically focus its work in the exact function I point it at, even when it's clear that adding a new helper would be a logical abstraction to share behaviour with the function right beside it.

Overall, I think it's probably better that it stay focused, and allow me to prompt it with "hey, go ahead and refactor these two functions" rather than the other way around. At the same time, really the ideal would be to have it proactively ask, or even pitch the refactor as a colleague would, like "based on what I see of this function, it would make most sense to XYZ, do you think that makes sense? "

Or perhaps even better, simply pursue both changes in parallel and present them as A/B options for the human reviewer to select between.

Re: Gemini 3.1 Pro

#264

Post by bratwurst3000 »

chankstein38 wrote: post #224
cowmoo728 wrote: post #198

Earlier quoted context omitted.

it's also so aggressive about taking out debug log statements and in-progress code. I'll ask it to fill in a new function somewhere else and it will remove all of the half written code from the piece I'm currently working on.

I ended up adding a "NEVER REMOVE LOGGING OR DEBUGGING INFO, OPT TO ADD MORE OF IT" to my user instructions and that has _somewhat_ fixed the problem but introduced a new problem where, no matter what I'm talking to it about, it tries to add logging. Even if it's not a code problem. I've had it explain that I could setup an ESP32 with a sensor so that I could get logging from it then write me firmware for it.

"I've had it explain that I could setup an ESP32 with a sensor so that I could get logging from it then write me firmware for it." lol did you try it? This so far from everything ratinonal

Re: Gemini 3.1 Pro

#265

Post by ac29 »

pqdbr wrote: post #222
jcims wrote: post #118

Pelican on a bicycle in drawio - https://imgur.com/a/tNgITTR (FWIW I'm finding a lot of utility in LLMs doing diagrams in tools like drawio)

How are you prompting it to draw diagrams in drawio

Drawio drawings are just XML, its possible it can generate that directly

Re: Gemini 3.1 Pro

#266

Post by gallerdude »

merlindru wrote: post #259
WarmWash wrote: post #255

3.1 Pro is the first model to correctly count the number of legs on my "five legged dog" test image. 3.0 flash was the previous best, getting it after a few prompts of poking. 3.1 got it on the first prompt though, with the prompt being "How many legs does the dog have? Count Carefully". However, it didn't get it on the first try with the original prompt (prompt: "How many legs does the dog have?"). It initially said…

your question may have become part of the training data with how much coverage there was around it. perhaps you should devise a new test :P

My job may have become part of the training data with how much coverage there is around it. Perhaps another career would be a better test of LLM capabilities.

Re: Gemini 3.1 Pro

#268

Post by neya »

embedding-shape wrote: post #73
simonw wrote: post #52

Pretty great pelican: https://simonwillison.net/2026/Feb/19/gemini-31-pro/ - took over 5 minutes though, but I think that's because they're having performance teething problems on launch day.

It's an excellent demonstration of the main issue I have with the Gemini family of models, they always go "above and beyond" to do a lot of stuff, even if I explicitly prompt against it. In this case, most of the SVG ends up consisting not just of a bike and a pelican, but clouds, a sun, a hat on the pelican and so much more. Exactly the same thing happens when you code, it's almost impossible to get Gemini to not do…

> it's almost impossible to get Gemini to not do "helpful" drive-by-refactors

This has not been my experience. I do Elixir primarily and Gemini has helped build some really cool products and massive refactors along the way. And it would even pick up security issues and potential optimizations along the way

What HAS been an issue constantly though was randomly the model will absolutely not respond at all and some random error would occur which is embarrassing for a company like Google with the infrastructure they own.

Re: Gemini 3.1 Pro

#269

Post by wat10000 »

merlindru wrote: post #259
WarmWash wrote: post #255

3.1 Pro is the first model to correctly count the number of legs on my "five legged dog" test image. 3.0 flash was the previous best, getting it after a few prompts of poking. 3.1 got it on the first prompt though, with the prompt being "How many legs does the dog have? Count Carefully". However, it didn't get it on the first try with the original prompt (prompt: "How many legs does the dog have?"). It initially said…

your question may have become part of the training data with how much coverage there was around it. perhaps you should devise a new test :P

Easy fix, make a new test image with six legs, and watch all the LLMs say it has five.
Post reply on HN