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

881–890 of 951 posts

Re: Gemini 3.1 Pro

#881

Post by embedding-shape »

Radle wrote: post #873
embedding-shape wrote: post #177

Earlier quoted context omitted.

> I'm pretty sure it writes comments for itself, not for the user Yeah, that sounds worse than "trying to helpful". Read the code instead, why add indirection in that way, just to be able to understand what other models understand without comments?

The Indirection is on purpose, it works like a continued chain of thought.

Yeah, I'm just doubtful Gemini could ever be considered a "better model" if it needs to put "chain of thought" artifacts into my source code, considering that none of the other models seems to need that to write better code than Gemini.

Re: Gemini 3.1 Pro

#882

Post by PratMish »

stephen_cagle wrote: post #470
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…

I also worked at Google (on the original Gemini, when it was still Bard internally) and my experience largely mirrors this. My finding is that Gemini is pretty great for factual information and also it is the only one that I can reliably (even with the video camera) take a picture of a bird and have it tell me what the bird is. But it is just pretty bad as a model to help with development, myself and everyone I know…

Gemini is pretty hit-or-miss with tool calls. Even when I explicitly ask for a code block, it tends to break the formatting and spill the text everywhere.

Re: Gemini 3.1 Pro

#883

Post by KoolKat23 »

mikestorrent wrote: post #568
small_model wrote: post #478

Earlier quoted context omitted.

I was being facetious, I mean one day models might skip the middle man of code and compilation and take your specs and produce an ultra efficent binary.

Musk was saying that recently but I don't see it being efficient or worthwhile to do this. I could be proven brutally wrong, but code is language; executables aren't. There's also no real reason to bother with this when we have quick-compiling languages. More realistically, I could see particular languages and frameworks proving out to be more well-designed and apt for AI code creation; for instance, I was always too…

Exactly this it serves little purpose.

You're going to need to spend crazy compute just compiling and obtaining training data. And until it's oneshotting absolutely everything. You're going to be asking it what it's it doing and then it'll be "uncompiling" it's code, I can't see this being more efficient than the other way compiling.

I suspect the actual benefit would be more in virtualised interfaces such as Genie 3, skipping this step altogether. Where it's just manipulating pixels and the pixels change based on the underlying statistical model output rather than old school computation.

Re: Gemini 3.1 Pro

#884

Post by MattRix »

datahack wrote: post #777
bluegatty wrote: post #589

Earlier quoted context omitted.

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…

I know this is only a partial answer, but I feel like Google is once again trying to build a product based on internal priorities, existing business protectionism, and internal business goals, rather than building a product that is listening actively to real use feedback as the primary priority. It is the company’s constant kryptonite. They seem to be, from my third part perspective, repeating the same ol’, same ol’…

The thing is that this is genuinely useful to Googlers as well. If they’re internally dogfooding their tools and models for coding, it seems likely that things will improve.

Re: Gemini 3.1 Pro

#885

Post by embedding-shape »

ionwake wrote: post #837
embedding-shape wrote: post #234

Earlier quoted context omitted.

> 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

It takes humanity to be able to get into other's perspectives. It takes experience and wisdom to be able to do so for animals too.

Re: Gemini 3.1 Pro

#886

Post by davedx »

datahack wrote: post #777
bluegatty wrote: post #589

Earlier quoted context omitted.

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…

I know this is only a partial answer, but I feel like Google is once again trying to build a product based on internal priorities, existing business protectionism, and internal business goals, rather than building a product that is listening actively to real use feedback as the primary priority. It is the company’s constant kryptonite. They seem to be, from my third part perspective, repeating the same ol’, same ol’…

If you're looking it through the lens of "agentic coding", then sure, Anthropic might be better than Gemini. But I use Gemini heavily for batch processing / web scraping workloads, and it's the only show in town there, really (because it's directly integrated into Google Search).

Re: Gemini 3.1 Pro

#887

Post by lunarboy »

KoolKat23 wrote: post #674
WarmWash wrote: post #626

Earlier quoted context omitted.

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…

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

Re: Gemini 3.1 Pro

#888

Post by xnx »

bluegatty wrote: post #598
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...

You can pay 1 cent for a mediocre answer or 2 cents for a great answer. So a lot of these things are relative. Now if that equation plays out 20K times a day, well that's one thing, but if it's 'once a day' then the cost basis becomes irrelevant. Like the cost of staplers for the Medical Device company. Obviously it will matter, but for development ... it's probably worth it to pay $300/mo for the best model, when th…

> You can pay 1 cent for a mediocre answer or 2 cents for a great answer.

But Gemini is also a great answer (possibly slightly less great or more great).

When consumers cannot easily assess a product's quality, they frequently use price as a primary indicator, equating higher costs with superior quality.

Re: Gemini 3.1 Pro

#889

Post by zobzu »

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…

same here (ex G and all that jazz). but in practice it means I use gemini for a lot of stuff, just not code. Claude wont try yo one shoot complex stuff that Gemini will + but claude will reliably produce what you expect.

Re: Gemini 3.1 Pro

#890

Post by xnx »

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…

> But man, people are really avid about it being an awful model.

If you told people Gemini 3.1 was Claude 4.7, they'd be going nuts singing its praises.

Post reply on HN