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

941–950 of 951 posts

Re: Gemini 3.1 Pro

#941

Post by bdelmas »

sigmoid10 wrote: post #594
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:…

For me it's Opus 4.6 for researching code/digging through repos, gpt 5.3 codex for writing code, gemini for single hardcore science/math algorithms and grok for things the others refuse to answer or skirt around (e.g. some security/exploitability related queries). Get yourself one of those wrappers that support all models and forget thinking about who has the best model. The question is who has the best model for you…

Yes I came to the same conclusion. Just to add: be careful with Opus 4.6 guys. It’s expensive…

Re: Gemini 3.1 Pro

#942

Post by andxor »

rudhdb773b wrote: post #933
andxor wrote: post #694

Earlier quoted context omitted.

Who are they supposed to compare it to? I'm not sure what makes you think that Grok is even remotely comparable to the frontier models right now.

Grok has been and still is the best at incorporating search. 4.20 with its 4 agents puts it back at the top for reasoning as well. As soon as it's added to the API, the benchmarks should show that.

I agree it's good for researching current events because of the integration with X.

Re: Gemini 3.1 Pro

#943

Post by vidarh »

cmrdporcupine wrote: post #929
vidarh wrote: post #928

Earlier quoted context omitted.

I think you underestimate how deep-seated the view of Google as liable to end-of-life any product at any time is for the outside world. I don't adopt any new Google products any more, because I have no reason to trust that it will stay around.

I think you didn't read what I wrote and are mistaking me for some sort of advocate for you adopting Google's products?

I didn't mistake you for that at all. I didn't give any thought at all to that, in fact.

My point was that this "more even than it did for the outside world" seemed to downplay how strongly this view of Google from the "outside world" is held.

I just found it amusing that people at Google would assume even my first comment was indicative of being at Google, much less my second comment, rather than being a totally normal thing for someone outside Google to think.

I'm not surprised to hear that this hold inside Google as well. You just don't need any inside knowledge of Google to hold this view.

Re: Gemini 3.1 Pro

#944

Post by SergeAx »

WarmWash wrote: post #626
sdeiley wrote: post #548

People underrate Google's cost effectiveness so much. Half price of Opus. HALF. Think about ANY other product and what you'd expect from the competition thats half the price. Yet people here act like Gemini is dead weight ____ Update: 3.1 was 40% of the cost to run AA index vs Opus Thinking AND SONNET, beat Opus, and still 30% faster for output speed. https://artificialanalysis.ai/?speed=intelligence-vs-speed&m...

Gemini is the most paradoxical model because it benchmarks great even in private benchmarks done by regular people, Deep Mind is unquestionably full of capable engineers with incredible skill, and personally Gemini has been great for my day job and my coding for fun (not for profit) endeavors. Switching between it and 4.6 in antigravity and I don't see much of a difference, they both do what I ask. But man, people ar…

All perceptions are very personal and anecdotal. Here's mine: I tried to rebuild a website from Hugo to Astro. Gemini 3.0 was mediocre and in the end just failed and was unable to complete the task. Sonnet did almost well. I had to flush the context once most of the job was finished, for atomic git commits and deployment scripts.

Re: Gemini 3.1 Pro

#946

Post by thallavajhula »

3371 wrote: post #757
thallavajhula wrote: post #669

This is great. I am hopeful that Gemini 3.1 Pro would be great. So far, I'm almost always pulled away from Gemini models by Claude. Having used Claude Opus High for a while now, Claude Opus seems to be fantastic at coding. Even Gemini's comparison chart says so. OpenAI's 5.3-codex is by far the weakest (of the 3) for my coding purposes. Claude Opus really shines at explanations and generating code. Gemini is almost g…

I would suggest you also take a look at Cursor's Composer1.5. It's super fast, and perform better than Gemini3P in my use cases.

I've been trying composer-1.5 on and off and it doesn't come close to Claude's Opus High. The explainability of Claude is just something else.

Re: Gemini 3.1 Pro

#947

Post by 3371 »

thallavajhula wrote: post #946
3371 wrote: post #757

Earlier quoted context omitted.

I would suggest you also take a look at Cursor's Composer1.5. It's super fast, and perform better than Gemini3P in my use cases.

I've been trying composer-1.5 on and off and it doesn't come close to Claude's Opus High. The explainability of Claude is just something else.

Sure, my point was it's better than Gemini and it's really really fast, and it's missing from the parent comment.

Re: Gemini 3.1 Pro

#948

Post by ac29 »

ojr wrote: post #891
Alex-Programs wrote: post #827

Earlier quoted context omitted.

I'm curious, what's the agent like? If I were to build something for Gemini models I'd plan around ingesting a bunch of context then oneshotting it.

you can run into payload too large errors, ingesting bunch of context, I use vercel's ai sdk so I can interchange between models but have 0 OpenAI and Claude credits or subscriptions. I use a combination of grepping files like a terminal tool and implemented a vector search database for fuzzy searches, Gemini chooses what tool it wants to use, I provide it create, read, update, delete, functions. There's a few tricks…

> Website: https://slidebits.com/isogen

You should really provide a comparison to existing agentic tools if you expect people to buy annual licenses to your tool. Right now pretty much all of your competition is free and a there are a lot of good open source agents as well.

The AI generated landing page is pretty lousy too, did you even review it? As an example, it says "40% off" of $199.99 = $99.99? Its also not clear if your pricing includes tokens. It says "unlimited generations" are included but also mentions using your own API key?

Re: Gemini 3.1 Pro

#949

Post by jbellis »

iCarrot wrote: post #721
jbellis wrote: post #274

Earlier quoted context omitted.

still no minimal reasoning in G3.1P :( (this is why Opus 4.6 is worth the price -- turning off thinking makes it 3x-5x faster but it loses only a small amount of intelligence. nobody else has figured that out yet)

You can turn off thinking in Gemini pro models by using completion mode. Essentially, append a message with role=model and minimal text part, such as a simple "A", at the end of the "contents" array. The model will try to complete the message without using any thought tokens. You can also set the model message to start with "think" or something along that line and watch it thinks out loud (or melts down with over-thi…

TIL gemini still supports completion mode, that's super useful!

Re: Gemini 3.1 Pro

#950

Post by cdelsolar »

embedding-shape wrote: post #229
cdelsolar wrote: post #182

Earlier quoted context omitted.

share

The harness? Trivial to build yourself, ask your LLM for help, it's ~1000 LOC you could hack together in 10-15 minutes. As for the test cases themselves, that would obviously defeat the purpose, so no :)

the purpose of what? i'm not an LLM
Post reply on HN