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

831–840 of 951 posts

Re: Gemini 3.1 Pro

#831

Post by qnleigh »

sheepscreek wrote: post #580

If it’s any consolation, it was able to one-shot a UI & data sync race condition that even Opus 4.6 struggled to fix (across 3 attempts). So far I like how it’s less verbose than its predecessor. Seems to get to the point quicker too. While it gives me hope, I am going to play it by the ear. Otherwise it’s going to be - Gemini for world knowledge/general intelligence/R&D and Opus/Sonnet 4.6 to finish it off. UPDATE:…

Interesting, I've had similar issues. It seems to be very clumsy when using its internal tooling. I've seen diffs where it accidentally garbled significant amounts of code, which it then had to go in and manually fix. It's also introduced bugs into features that it wasn't supposed to be touching, and when I asked it why it was making changes to I the other code, it answered that it had failed to copy-paste since large blocks of code correctly.

Re: Gemini 3.1 Pro

#832

Post by Grisu_FTP »

Mashimo wrote: post #796
Grisu_FTP wrote: post #795

Somehow the models apparently get better and better every week, but every time i try to use them they get worse. Am I the issue? Am i just misremembering the early times because it was a new thing?

You are holding it wrong! No but for real, what is your usecase? Do you acutely think something like gpt3 was best?

I dont have a real special usecase, i just use it whenever i think it will give better results than googling or thinking or i dont feel like getting annoyed by cookie popups.

And i dont think gpt3 was best, but it felt like it actually listened. Now i tell it: "You did this and this wrong, i specifically told u the exact opposite. Can you please do what i asked you?" And then it says something like: "Oh yes my bad, you are right and very very smart to have caught that you must be a super genius. I will now do what you asked me" Does the same wrong thing again. and again and again.

I ask it to fix a mistake, it tells me it fixed it, gives 1:1 the same thing with more errors.

It also feels like it forgets mid convo way faster than it did.

Re: Gemini 3.1 Pro

#833

Post by niek_pas »

motoboi wrote: post #750
ttul wrote: post #709

What I’m noticing, overall: I’ve never cut so much code in my life. I’ve become a coding monster with one of those dark green GitHub profiles ever since 5.3-Codex gave me the confidence to load in a ridiculous number of tasks every day and let it rip. I have about three coding tasks going at once and in another window, Claude Cowork is ripping through PowerPoints and getting back to lawyers. This tech is not going to…

There are thousands like you now. How many does it take to run the economy? What would the rest do. Think of it like what a tractor did to agricultural work. The fist guy that used a tractor probably thought: this is not replacing me, I’m just much more productive. Well, turns out you only need one guy per farm now.

The market for iOS todo-applications seems to be infinite, so everyone can just become a todo app developer.

Re: Gemini 3.1 Pro

#834

Post by rahulroy »

In the meantime, I'm trying to update Antigravity to use the latest version, but it just wouldn't update itself, nor would it let me use 3.0 model. I restarted multiple times with the same result.

I tried telling this to agent, and it keeps repeating the same phrase "Gemini 3.1 Pro is not available on this version. Please upgrade to the latest version."

Congratulations on beating the benchmarks, but I wonder how much effort is devoted on improving DX?

Edit: It's updated now, I can confirm with "There are currently no updates available.". It still doesn't let me continue with the conversation. I'm able to create new session though.

Re: Gemini 3.1 Pro

#835

Post by Certhas »

weatherlite wrote: post #784
ethbr1 wrote: post #758

Earlier quoted context omitted.

Google hasn't seen its legacy ad revenue start to dent until products with built-in agents start to see mass adoption. Writing is on the wall that orders of magnitude fewer people will be going to google.com or using an interactive Google search in the next 5 years though.

LLMs are pretty mediocre for a lot of money queries like searching to buy shoes, looking at flights etc due to them not being up to date. So sure you can use them as a wrapper on top of Google but I assume a huge chunk of people will just go to Google to do that or use Google agents. Chrome will prove a very valuable asset for that - the whole experience can become agentic and Google is very well positioend to conver…

LLMs can execute searches? You can absolutely send ChatGPT to look for a cheap flight and it will do pretty well. And because I am paying for ChatGPT rather than the advertiser's, I am the customer and not the product.

Re: Gemini 3.1 Pro

#836

Post by Mashimo »

Grisu_FTP wrote: post #832
Mashimo wrote: post #796

Earlier quoted context omitted.

You are holding it wrong! No but for real, what is your usecase? Do you acutely think something like gpt3 was best?

I dont have a real special usecase, i just use it whenever i think it will give better results than googling or thinking or i dont feel like getting annoyed by cookie popups. And i dont think gpt3 was best, but it felt like it actually listened. Now i tell it: "You did this and this wrong, i specifically told u the exact opposite. Can you please do what i asked you?" And then it says something like: "Oh yes my bad, y…

> I ask it to fix a mistake, it tells me it fixed it, gives 1:1 the same thing with more errors.

> It also feels like it forgets mid convo way faster than it did.

Mhh, I don't observe this. Hard to say.

You probably know this already, but be sure to don't reuse a AI conversation with different context (Having a single chat for both cooking and coding is nono). Often starting a new chat is better.

If it forgets what you said it sounds a bit like you use one chat for too long, or you use a too small model (fast, air, haiku, nano etc.)

Re: Gemini 3.1 Pro

#837

Post by ionwake »

embedding-shape wrote: post #234
coldtea wrote: post #101

Earlier quoted context omitted.

It's a pelican. What do you expect a pelican to have in his bike's basket? It's a pretty funny and coherent touch!

> What do you expect a pelican to have in his bike's basket? Probably stuff it cannot fit in the gullet, or don't want there (think trash). I wouldn't expect a pelican to stash fish there, that's for sure.

hold on guys, what we have here is a cycling pelican expert

Re: Gemini 3.1 Pro

#838

Post by irthomasthomas »

cyanydeez wrote: post #639
irthomasthomas wrote: post #550

Earlier quoted context omitted.

i would say this is a lower difficulty. the car question primes it to think about stuff like energy and pollution.

Ok, but the point of the logical question is about the connection. If you really think it's answering logically with reasoning, there should be zero priming.

its not primed to help, its primed to confuse. models want to be good responsible people who care about the environment and don't waste fuel. that primes it to want to walk and it has to use "reasoning" to break out of that. thats what makes it harder, it has to fight between the logical answer and the 'responsible' answer. with the elephant question there is no such conflict.

Re: Gemini 3.1 Pro

#839

Post by ionwake »

vnglst wrote: post #449

I asked Gemini 3.1 Pro to generate some of the modern artworks in my "Pelican Art Gallery". I particularly like the rendition of the Sunflowers: https://pelican.koenvangilst.nl/gallery/category/modern

bro why is called pelican art gallery if you have no pelican art in it.

Is this like 5d chess layers of irony or something im not getting through?

Nice gallery besides

Re: Gemini 3.1 Pro

#840

Post by mcintyre1994 »

tkuraku wrote: post #764
bugfix wrote: post #688

Earlier quoted context omitted.

Do they offer a subscription like Claude? These models waste so many tokens "thinking", that using via API is a complete waste of money.

https://one.google.com/about/google-ai-plans/?utm_source=g1&...

At least Anthropic tells you how many more tokens you’re paying for! 5x 10x 20x whatever. Google seems to just say more, higher, highest.
Post reply on HN