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

161–170 of 951 posts

Re: Gemini 3.1 Pro

#161

Post by WarmWash »

embedding-shape wrote: post #137
gavinray wrote: post #119

Earlier quoted context omitted.

Do you have Personalization Instructions set up for your LLM models? You can make their responses fairly dry/brief.

I'm mostly using them via my own harnesses, so I have full control of the system prompts and so on. And no matter what I try, Gemini keeps "helpfully" adding code comments every now and then. With every other model, "- Don't add code comments" tends to be enough, but with Gemini I'm not sure how I could stop the comments from eventually appearing.

I'm pretty sure it writes comments for itself, not for the user. I always let the models comment as much as they want, because I feel it makes the context more robust, especially when cycling contexts often to keep them fresh.

There is a tradeoff though, as comments do consumer context. But I tend to pretty liberally dispense of instances and start with a fresh window.

Re: Gemini 3.1 Pro

#162

Post by davidguetta »

Implementation and Sustainability Hardware: Gemini 3 Pro was trained using Google’s Tensor Processing Units (TPUs). TPUs are specically designed to handle the massive computations involved in training LLMs and can speed up training considerably compared to CPUs. TPUs often come with large amounts of high-bandwidth memory, allowing for the handling of large models and batch sizes during training, which can lead to better model quality. TPU Pods (large clusters of TPUs) also provide a scalable solution for handling the growing complexity of large foundation models. Training can be distributed across multiple TPU devices for faster and more efficient processing.

So google doesn't use NVIDIA GPUs at all ?

Re: Gemini 3.1 Pro

#163

Post by metal_am »

gavinray wrote: post #119
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…

Do you have Personalization Instructions set up for your LLM models? You can make their responses fairly dry/brief.

I'd love to hear some examples!

Re: Gemini 3.1 Pro

#164

Post by benatkin »

takoid wrote: post #43
sho_hn wrote: post #11

Earlier quoted context omitted.

The touted SVG improvements make me excited for animated pelicans.

I just gave it a shot and this is what I got: https://codepen.io/takoid/pen/wBWLOKj The model thought for over 5 minutes to produce this. It's not quite photorealistic (some parts are definitely "off"), but this is definitely a significant leap in complexity.

Here's what I got from Gemini Pro on gemini.google.com, it thought for under a minute...might you have been using AI studio? https://jsbin.com/zopekaquga/edit?html,output

It does say 3.1 in the Pro dropdown box in the message sending component.

Re: Gemini 3.1 Pro

#165

Post by wahnfrieden »

rubicon33 wrote: post #117
onlyrealcuzzo wrote: post #111

We've gone from yearly releases to quarterly releases. If the pace of releases continues to accelerate - by mid 2027 or 2028 we're headed to weekly releases.

But actual progress seems to be slower. These modes are releasing more often but aren’t big leaps.

GPT 5.3 (/Codex) was a huge leap over 5.2 for coding

Re: Gemini 3.1 Pro

#166

Post by HPsquared »

steve_adams_86 wrote: post #106
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.

Ugh, the gears and chain don't mesh and there's no sprocket on the rear hub But seriously, I can't believe LLMs are able to one-shot a pelican on a bicycle this well. I wouldn't have guessed this was going to emerge as a capability from LLMs 6 years ago. I see why it does now, but... It still amazes me that they're so good at some things.

And the left leg is straight while the right leg is bent.

EDIT: And the chain should pass behind the seat stay.

Re: Gemini 3.1 Pro

#167

Post by foruhar »

seizethecheese wrote: post #130

I use Gemini flash lite in a side project, and it’s stuck on 2.5. It’s now well behind schedule. Any speculation as to what’s going on?

Gemini-3.0-flash-preview came out right away with the 3.0 release and I was expecting 3.0-flash-lite before a bump on the pro model. I wonder if they have abandoned that part of the Pareto/price-performance.

Re: Gemini 3.1 Pro

#169

Post by gavinray »

metal_am wrote: post #163
gavinray wrote: post #119

Earlier quoted context omitted.

Do you have Personalization Instructions set up for your LLM models? You can make their responses fairly dry/brief.

I'd love to hear some examples!

I use LLM's outside of work primarily for research on academic topics, so mine is:

  Be a proactive research partner: challenge flawed or unproven ideas with evidence; identify inefficiencies and suggest better alternatives with reasoning; question assumptions to deepen inquiry.

Re: Gemini 3.1 Pro

#170

Post by azuanrb »

The CLI needs work, or they should officially allow third-party harnesses. Right now, the CLI experience is noticeably behind other SOTA models. It actually works much better when paired with Opencode.

But with accounts reportedly being banned over ToS issues, similar to Claude Code, it feels risky to rely on it in a serious workflow.

Post reply on HN