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

891–900 of 951 posts

Re: Gemini 3.1 Pro

#891

Post by ojr »

Alex-Programs wrote: post #827
ojr wrote: post #723

Earlier quoted context omitted.

I primarily use Gemini 3 Flash with a GUI coding agent I made by myself and its been able to successfully one-shot mostly any task I throw at it. Why would I ever use a more expensive reasoning and slower reasoning model? I am impressed with the library knowledge Gemini knows, I don't use any skills or MCP and its able to implement functions to perfection. No one crawls more data than Google and their model reflects…

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 I do as well but if I tell you, you can probably prompt a clone . Sharing the full implementation is basically open sourcing the code.

Demo: https://www.youtube.com/watch?v=jKMrvh56F0M Website: https://slidebits.com/isogen

if you want to try it out let me know, I'll provide free access and a gemini test key

https://slidebits.com/support

Re: Gemini 3.1 Pro

#892

Post by otabdeveloper4 »

Certhas wrote: post #835
weatherlite wrote: post #784

Earlier quoted context omitted.

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.

> You can absolutely send ChatGPT to look for a cheap flight and it will do pretty well.

Sure, once they figure out how to count to three.

Re: Gemini 3.1 Pro

#893

Post by ojr »

port11 wrote: post #804
ojr wrote: post #723

Earlier quoted context omitted.

I primarily use Gemini 3 Flash with a GUI coding agent I made by myself and its been able to successfully one-shot mostly any task I throw at it. Why would I ever use a more expensive reasoning and slower reasoning model? I am impressed with the library knowledge Gemini knows, I don't use any skills or MCP and its able to implement functions to perfection. No one crawls more data than Google and their model reflects…

My experience with Antigravity was that 3 Pro can reason itself out of Gemini’s typical loops, but won’t actually achieve it (it gets stuck). 3 Flash usually doesn't get into any loops, but then again, it’s also not really following prompts properly. I’ve tried all manner of harnesses around what it shouldn’t do, but it often ignores some instructions. It also doesn’t follow design specs at all, it will output React…

I don't use Stitch it doesn't have the context of my codebase, I just tell Gemini to make the UI directly and its able to do it. The only time it failed is when my prompt and goal was bad. I told it to swap expo-audio with react-native-track-player and it was able to do it in one-shot. Implement Revenue Cat and it did it in one shot. I do task by task like all the other agent tools recommended. The harness I made doesn't install packages, it just provides code. I don't use Anitgravity or any Electron-based coding agent, mine has a Rust core and different prompt engineering, not sure why it works so well but it does.

Demo: https://www.youtube.com/watch?v=jKMrvh56F0M Website: https://slidebits.com/isogen

I need to implement a better free trial plan, it's reached enough maturity where its my only and primary way I write code, I also use web chats to help me craft prompts. Reach out to test. https://slidebits.com/support

Re: Gemini 3.1 Pro

#894

Post by esoterae »

bluegatty wrote: post #589
spankalee wrote: post #199

I hope this works better than 3.0 Pro I'm a former Googler and know some people near the team, so I mildly root for them to at least do well, but Gemini is consistently the most frustrating model I've used for development. It's stunningly good at reasoning, design, and generating the raw code, but it just falls over a lot when actually trying to get things done, especially compared to Claude Opus. Within VS Code Copi…

Yes, this is very true and it speaks strongly to this wayward notion of 'models' - it depends so much on the tuning, the harness, the tools. I think it speaks to the broader notion of AGI as well. Claude is definitively trained on the process of coding not just the code, that much is clear. Codex has the same limitation but not quite as bad. This may be a result of Anthropic using 'user cues' with respect to what are…

The full aphorism is:

Jack of all trades, master of none, is oftentimes better than master of one.

Re: Gemini 3.1 Pro

#895

Post by km144 »

moffkalast wrote: post #541
maxall4 wrote: post #81

Earlier quoted context omitted.

Theoretically, you can’t benchmaxx ARC-AGI, but I too am suspect of such a large improvement, especially since the improvement on other benchmarks is not of the same order.

https://arcprize.org/arc-agi/1/ It's a sort of arbitrary pattern matching thing that can't be trained on in the sense that the MMLU can be, but you can definitely generate billions of examples of this kind of task and train on it, and it will not make the model better on any other task. So in that sense, it absolutely can be. I think it's been harder to solve because it's a visual puzzle, and we know how well today's…

The real question is: Why are people designing benchmarks that, if a model is trained on them, it won't improve the performance of the model at any real-world tasks? Why would anyone care about such benchmarks?

Re: Gemini 3.1 Pro

#896

Post by startages »

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...

This is misleading. I'm running a live experiment here: https://project80.divcrafts.com/

There are 4 models, all receiving the exact same prompts a few times a day, required to respond with a specific action.

In the first experiment I used gemini-3-pro-preview, it spent ~$18 on the same task where Opus 4.5 spent ~$4, GPT-5.1 spent ~$4.50, and Grok spent ~$7. Pro was burning through money so fast I switched to gemini-3-flash-preview, and it's still outspending every other model on identical prompts. The new experiment is showing the same pattern.

Most of the cost appears to be reasoning tokens.

The takeaway here is: Gemini spends significantly more on reasoning tokens to produce lower quality answers, while Opus thinks less and delivers better results. The per-token price being lower doesn't matter much when the model needs 4x the tokens to get there.

Re: Gemini 3.1 Pro

#897

Post by embedding-shape »

girvo wrote: post #540
quotemstr wrote: post #299

Earlier quoted context omitted.

What. You don't have yours ask for edit approval?

The depressing truth is most I know just run all these tools in /yolo mode or equivalents. Because your coworkers definitely are, and we're stack ranked, so it's a race (literally) to the bottom. Just send it... (All this actually seems to do is push the burden on to their coworkers as reviewers, for what it's worth)

You're mixing up two things though. One is what the agent does "locally", wherever that might be (for me it's inside a VM), and second is what code you actually share or as you call "send".

Just because you don't want to gate every change in #1, doesn't mean you're just throwing shit via #2, I'm still reviewing my code as much as before, if not more now, before I consider it ready to be reviewed by others.

But I'm seemingly also one of the few developers who seem to take responsibility of the code I produce, even if AI happens to have coded it.

Re: Gemini 3.1 Pro

#898

Post by KoolKat23 »

lunarboy wrote: post #887
KoolKat23 wrote: post #674

Earlier quoted context omitted.

Outside of code, Gemini is really really good.

It's so weird. I actually prefer the web version for generic questions like "how would I do X in git" or something, and it'll answer it well. Gemini CLI will immediately try to run git log on the entire graph, grep every single file in the repo, like just answer the question. I actually put in gemini.md to just answer first without running other commands unless explicitly requested and it's been a lot better

Thanks for this suggestion, it's actually been my experience too.

Re: Gemini 3.1 Pro

#899

Post by segmondy »

energy123 wrote: post #321
ripbozo wrote: post #22

Earlier quoted context omitted.

Does the arc-agi-2 score more than doubling in a .1 release indicate benchmark-maxing? Though i dont know what arc-agi-2 actually tests

Francois Chollet accuses the big labs of targeting the benchmark, yes. It is benchmaxxed.

He should have kept it closed.

Re: Gemini 3.1 Pro

#900

Post by tourist2d »

startages wrote: post #896
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...

This is misleading. I'm running a live experiment here: https://project80.divcrafts.com/ There are 4 models, all receiving the exact same prompts a few times a day, required to respond with a specific action. In the first experiment I used gemini-3-pro-preview, it spent ~$18 on the same task where Opus 4.5 spent ~$4, GPT-5.1 spent ~$4.50, and Grok spent ~$7. Pro was burning through money so fast I switched to gemini-…

[dead]
Post reply on HN