Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 2.5 Flash

developers.googleblog.com

Post reply on HN
Print view View original

441–450 of 582 posts

Re: Gemini 2.5 Flash

#441

Post by instagraham »

zoogeny wrote: post #131

Google making Gemini 2.5 Pro (Experimental) free was a big deal. I haven't tried the more expensive OpenAI models so I can't even compare, only to the free models I have used of theirs in the past. Gemini 2.5 Pro is so much of a step up (IME) that I've become sold on Google's models in general. It not only is smarter than me on most of the subjects I engage with it, it also isn't completely obsequious. The model push…

obsequious is such a nice word for this context, only possible in the AI age.

i'd find the same word improper to describe human beings - other words like plaintive, obedient and compliant often do the job better and are less obscure.

here it feels like a word whose time has come.

Re: Gemini 2.5 Flash

#442

Post by brookst »

snthpy wrote: post #397
tkgally wrote: post #254

Earlier quoted context omitted.

Another useful word in this context is “sycophancy,” meaning excessive flattery or insincere agreement. Amanda Askell of Anthropic has used it to describe a trait they try to suppress in Claude: https://youtube.com/watch?v=ugvHCXCOmm4&t=10286

Interesting that Americans appear to hold their AI models to a higher standard than their politicians.

Different Americans.

Re: Gemini 2.5 Flash

#443

Post by yousif_123123 »

mamp wrote: post #237
jeeeb wrote: post #192

Earlier quoted context omitted.

After comparing Gemini Pro and Claude Sonnet 3.7 coding answers side by side a few times, I decided to cancel my Anthropic subscription and just stick to Gemini.

I've been using Gemini 2.5 and Claude 3.7 for Rust development and I have been very impressed with Claude, which wasn't the case for some architectural discussions where Gemini impressed with it's structure and scope. OpenAI 4.5 and o1 have been disappointing in both contexts. Gemini doesn't seem to be as keen to agree with me so I find it makes small improvements where Claude and OpenAI will go along with initial su…

I have noticed Gemini not accepting an instruction to "leave all other code the same but just modify this part" on a code that included use of an alpha API with a different interface than what Gemini knows is the correct current API. No matter how I promoted 2.5 pro, I couldn't get it to respect my use of the alpha API, it would just think I must be wrong.

So I think patterns from the training data are still overriding some actual logic/intelligence in the model. Or the Google assistant fine-tuning is messing it up.

Re: Gemini 2.5 Flash

#444

Post by int_19h »

Asraelite wrote: post #419
int_19h wrote: post #414

Earlier quoted context omitted.

I used to use them mostly in "smart code completion" mode myself until very recently. But with all the AI IDEs adding agentic mode, I was curious to see how well that fares if I let it drive. And we aren't talking about trivial bugs here. For TypeScript, the most impressive bug it handled to date was an async race condition due to missing await causing a property to be overwritten with invalid value. For that one I a…

I use it for basically everything I can, not just code completion, including end-to-end bug fixes when it makes sense. But most of the time even the current Gemini and Claude models fail with the hard things. It might be because most bugs that you would encounter in other languages don't occur in the first place in Rust because of the stronger type system. The race condition one you mentioned wouldn't be possible for…

Race conditions can span across processes (think async process communication).

That said I do wonder if the problems you're seeing are simply because there isn't that much Rust in the training set for the models - because, well, there's relatively little of it overall when you compare it to something like C++ or JS.

Re: Gemini 2.5 Flash

#445

Post by rat9988 »

UltraSane wrote: post #266
zoogeny wrote: post #131

Google making Gemini 2.5 Pro (Experimental) free was a big deal. I haven't tried the more expensive OpenAI models so I can't even compare, only to the free models I have used of theirs in the past. Gemini 2.5 Pro is so much of a step up (IME) that I've become sold on Google's models in general. It not only is smarter than me on most of the subjects I engage with it, it also isn't completely obsequious. The model push…

I had a very interesting long debate/discussion with Gemini 2.5 Pro about the Synapse-Evolve bank debacle among other things. It really feels like debating a very knowledgeable and smart human.

You didn't have a debate, you just researched a question.

Re: Gemini 2.5 Flash

#446

Post by dcre »

nolok wrote: post #394
dcre wrote: post #43

Earlier quoted context omitted.

You can get an API key and they don't bill you. Free tier rate limits for some models (even decent ones like Gemini 2.0 Flash) are quite high. https://ai.google.dev/gemini-api/docs/pricing https://ai.google.dev/gemini-api/docs/rate-limits#free-tier

I'm pretty sure that's a google maps' level of free where once in control they will massively bill it

There is no reason to expect the other entrants in the market to drop out and give them monopoly power. The paid tier is also among the cheapest. People say it’s because they built their own their inference hardware and are genuinely able to serve it cheaper.

Re: Gemini 2.5 Flash

#447

Post by mdp2021 »

jay_kyburz wrote: post #215
mdp2021 wrote: post #157

Earlier quoted context omitted.

Grading papers definitely requires intelligence.

My partner marked a PHD thesis yesterday and there was a spelling mistake in the title. There is some level of analysis and feedback than an LLM could provide before a human reviews it. Even if it's just a fancy spelling checker.

I'd like to burst into a post a number of the unbelievable akin mishandlings of academic tasks I was reported, but. I do have a number of prize-worthy anecdotes that compete with yours. Nonetheless. Let us fight farce with rigour.

Even when the tasks are not in-depth, but easier to assess, you still require a /reliable evaluator/. LLMs are not. Could they be at least employed as a virtual assistant, "parse and suggest, then I'll check"? If so, not randomly ("pick a bot"), but in full awareness of the specific instrument. That stage is not here.

Re: Gemini 2.5 Flash

#448

Post by thimabi »

_delirium wrote: post #387
thimabi wrote: post #225

I find it baffling that Google offers such impressive models through the API and even the free AI Studio with fine-grained control, yet the models used in the Gemini app feel much worse. Over the past few weeks, I’ve been using Gemini Advanced on my Workspace account. There, the models think for shorter times, provide shorter outputs, and even their context window is far from the advertised 1 million tokens. It makes…

This might have changed after you posted your comment, but it looks like 2.5 Pro and 2.5 Flash are available in the Gemini app now, both web and mobile.

Oh, I didn’t mean to say that these models were unavailable through the app or website. Rather, I’ve realized that using them through the API or AI Studio yields much better results — even in the free tier.

You can check that by trying prompts with complex instructions and long inputs/outputs.

For instance, ask Gemini to generate notes from a specific source (say, a book or class transcription). Or ask it to translate a long article, full of idiomatic expressions, while maintaining high fidelity to the source. You will see that the very same Gemini models are underutilized on the app or the website, while their performance is stellar on the API or AI Studio.

Re: Gemini 2.5 Flash

#449

Post by neuah »

bayarearefugee wrote: post #278
blueyes wrote: post #229

Earlier quoted context omitted.

One of the main advantages Anthropic currently has over Google is the tooling that comes with Claude Code. It may not generate better code, and it has a lower complexity ceiling, but it can automatically find and search files, and figure out how to fix a syntax error fast.

As another person that cancelled my Claude and switched to Gemini, I agree that Claude Code is very nice, but beyond some initial exploration I never felt comfortable using it for real work because Claude 3.7 is far too eager to overengineer half-baked solutions that extend far beyond what you asked it to do in the first place. Paying real API money for Claude to jump the gun on solutions invalidated the advantage of…

Exactly my experience as well. Started out loving it but it almost moves too fast - building in functionality that i might want eventually but isn't yet appropriate for where the project is in terms of testing, or is just in completely the wrong place in the architecture. I try to give very direct and specific prompts but it still has the tendency to overreach. Of course it's likely that with more use i will learn better how to rein it in.

Re: Gemini 2.5 Flash

#450

Post by sleiben »

jeeeb wrote: post #192
zoogeny wrote: post #131

Google making Gemini 2.5 Pro (Experimental) free was a big deal. I haven't tried the more expensive OpenAI models so I can't even compare, only to the free models I have used of theirs in the past. Gemini 2.5 Pro is so much of a step up (IME) that I've become sold on Google's models in general. It not only is smarter than me on most of the subjects I engage with it, it also isn't completely obsequious. The model push…

After comparing Gemini Pro and Claude Sonnet 3.7 coding answers side by side a few times, I decided to cancel my Anthropic subscription and just stick to Gemini.

Same here. Especially for native app development with swift I had way better results and just sticked with Gemini-2.5-*
Post reply on HN