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

581–590 of 951 posts

Re: Gemini 3.1 Pro

#581

Post by embedding-shape »

well_ackshually wrote: post #482
embedding-shape wrote: post #313

Earlier quoted context omitted.

Who has time for that? This is how I run codex: `codex --sandbox danger-full-access --dangerously-bypass-approvals-and-sandbox --search exec "$PROMPT"`, having to approve each change would effectively destroy the entire point of using an agent, at least for me. Edit: obviously inside something so it doesn't have access to the rest of my system, but enough access to be useful.

>Who has time for that? People that don't put out slop, mostly.

That's another thing entirely, I still review and manually decide the exact design and architecture of the code, with more care now than before. Doesn't mean I want the UI of the agent to need manual approval of each small change it does.

Re: Gemini 3.1 Pro

#582

Post by sdeiley »

csmpltn wrote: post #574
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...

> "People underrate Google's cost effectiveness so much. Half price of Opus. HALF." Google undercutting/subsidizing it's own prices to bite into Anthropic's market share (whilst selling at a loss) doesn't automatically mean Google is effective.

Everybody is subsidizing their prices.

But Flash is 1/8 the cost of sonnet and its not impressive?

Re: Gemini 3.1 Pro

#583

Post by embedding-shape »

quotemstr wrote: post #353
embedding-shape wrote: post #313

Earlier quoted context omitted.

Who has time for that? This is how I run codex: `codex --sandbox danger-full-access --dangerously-bypass-approvals-and-sandbox --search exec "$PROMPT"`, having to approve each change would effectively destroy the entire point of using an agent, at least for me. Edit: obviously inside something so it doesn't have access to the rest of my system, but enough access to be useful.

I wouldn't even think of letting an agent work in that made. Even the best of them produce garbage code unless I keep them on a tight leash. And no, not a skill issue. What I don't have time to do is debug obvious slop.

I keep it on a tight leash too, not sure how that's related. What gets edited on disk is very different from what gets committed.

Re: Gemini 3.1 Pro

#584

Post by slopinthebag »

mikestorrent wrote: post #553
slopinthebag wrote: post #289

Earlier quoted context omitted.

Hmm, interesting.. My workflow is to basically use it to explain new concepts, generate code snippets inline or fill out function bodies, etc. Not really generating code autonomously in a loop. Do you think it would excel at this?

I think that you should really try to get whatever agent you can to work on that kind of thing for you - guide it with the creation of testing frameworks and code coverage, focus more on the test cases with your human intellect, and let it work to pass them.

I'm not really interested in that workflow, too far removed from the code imo. I only really do that for certain tasks with a bunch of boilerplate, luckily I simply don't use languages or frameworks that require very much BS anymore.

Re: Gemini 3.1 Pro

#585

Post by hobofan »

mike97 wrote: post #453
hobofan wrote: post #251

Earlier quoted context omitted.

> despite having virtually infinite processing power, money Just because they have the money doesn't mean that they spend it excessively. OpenAI and Anthropic are both offering coding plans that are possibly severely subsidized, as they are more concerned with growth at all cost, while Google is more concerned with profitability. Google has the bigger warchest and could just wait until the other two run out of money…

> OpenAI and Anthropic are both offering coding plans that are possibly severely subsidized So does Google, in fact I believe their antigravity limits for Opus and Sonnet for the $20 plan has higher limits than CC $20 plan, and there is no weekly cap or I couldn't get it even with heavy usage, and then you have a separate limit for Gemini cli and for other models from antigravity.

Is that so? I haven't personally used Antigravity, I just heard a lot of people complaining as recently as ~1 month ago that they hit the rate limits very quickly by e.g. it accidentally reading in too large files.

Re: Gemini 3.1 Pro

#586

Post by sdeiley »

mritchie712 wrote: post #573
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...

It's half the price per token. Not all tokens are generated equally.

Neither are cars but Ill take a Porsche over a Ferrari for a fraction of the price.

Re: Gemini 3.1 Pro

#587

Post by knicholes »

mclau153 wrote: post #437
nickandbro wrote: post #51

Does well on SVGs outside of "pelican riding on a bicycle" test. Like this prompt: "create a svg of a unicorn playing xbox" https://www.svgviewer.dev/s/NeKACuHj Still some tweaks to the final result, but I am guessing with the ARC-AGI benchmark jumping so much, the model's visual abilities are allowing it to do this well.

can we move on from SVG to 3D models at some point?

Image to model is already a thing, and it's pretty good.

Re: Gemini 3.1 Pro

#588

Post by rubicon33 »

wahnfrieden wrote: post #165
rubicon33 wrote: post #117

Earlier quoted context omitted.

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

Eh, sure, but marginally better if not the same as Claude 4.6, which itself was a small bump over Claud 4.5

Re: Gemini 3.1 Pro

#589

Post by bluegatty »

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 good completions and not, and feeding that into the tuning, among other things.

Anthropic is winning coding and related tasks because they're focused on that, Google is probably oriented towards a more general solution, and so, it's stuck in 'jack of all trades master of none' mode.

Post reply on HN