If OpenAI offers Codex and Anthropic offers Claude Code, is there a CLI integration that Google recommends for using Gemini 2.5? That’s what’s keeping me, for now, with the other two.
Gemini 2.5 Flash
381–390 of 582 posts
Re: Gemini 2.5 Flash
#382Google 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 Thanks for the new word, I have to look it up. "obedient or attentive to an excessive or servile degree" Apparently it means an AI that mindlessly follow your logic and instructions without reasoning and articulation is not good enough.
I wonder if anyone here will know this one;
I learned the word "obsequious" over a decade ago while working the line of a restaurant. I used to listen to the 2p2 (2 plus 2) poker podcasts during prep and they had a regular feature with David Sklansky (iirc) giving tips, stories, advice etc. This particular one he simply gave the word "obsequious" and defined it later. I remember my sous chef and I were debating what it could mean and I guessed it right. I still can't remember what it had to do with poker, but that's besides the point.
Maybe I can locate it
Re: Gemini 2.5 Flash
#383Genuine naive question: when it comes to Google HN has generally a negative view of it (pick any random story on Chrome, ads, search, web, working at faang, etc. and this should be obvious from the comments), yet when it comes to AI there is a somewhat notable “cheering effect” for Google to win the AI race that goes beyond a conventional appreciation of a healthy competitive landscape, which may appear as a bit of a…
The key is Gemini being free through AI Studio. This makes their technical improvement more impressive when OpenAI sells their best models at ridiculous prices.
If Google engages in price dumping as a monopolist remains to be seen but it feels like it.
The LLM race is fast paced and no moat has developed. People are switching on a whim if better models (by some margin) show up. When will OpenAI, Anthropic or DeepSeek counter 2.5 Pro? And will it be before Google releases the next Pro?
OpenAI commands a large chunk of the consumer market and they have considerable funds after their last round. They won't fold this or next year.
If Google wants to win this they must come up with a product strategy integrating their search business without seriously damaging their existing search business to much. This is hard.
Re: Gemini 2.5 Flash
#384Earlier quoted context omitted.
i have a high volume task i wrote an eval for and was pleasantly surprised at 2.0 flash's cost to value ratio especially compared to gpt4.1-mini/nano accuracy | input price | output price Gemini Flash 2.0 Lite: 67% | $0.075 | $0.30 Gemini Flash 2.0: 93% | $0.10 | $0.40 GPT-4.1-mini: 93% | $0.40 | $1.60 GPT-4.1-nano: 43% | $0.10 | $0.40 excited to to try out 2.5 flash
Can I ask a serious question. What task are you writing where its ok to get 7% error rate. I can't get my head around how this can be used.
I expect some manual correction after the work is done. I actually mentally counted all the times I pressed backspace while writing this paragraph, and it comes down to 45. I'm not counting the next paragraph or changing the number.
Humans make a ton of errors as well. I didn't even notice how many I was making here until I started counting it. AI is super useful to just write get a first draft out, not for the final work.
Re: Gemini 2.5 Flash
#385Earlier quoted context omitted.
100% agree. I had Gemini flash 2 chew through thousands of points of nasty unstructured client data and it did a 'better than human intern' level conversion into clean structured output for about $30 of API usage. I am sold. 2.5 pro experimental is a different league though for coding. I'm leveraging it for massive refactoring now and it is almost magical.
what tool are you using 2.5-pro-exp through? Cline? Or the browser directly?
Copilot experimental (need VSCode Insiders) has it. I‘ve thought about trying aider —-watch-files though, also works with multiple files.
Re: Gemini 2.5 Flash
#386I just asked "why is 'Good Friday' so called?" and it got stuck. Flash 2.0 worked though.
Re: Gemini 2.5 Flash
#387I 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.
Re: Gemini 2.5 Flash
#388Earlier 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 have had a few epic refactoring failures with Gemini relative to Claude. For example: I asked both to change a bunch of code into functions to pass into a `pipe` type function, and Gemini truly seemed to have no idea what it was supposed to do, and Claude just did it. Maybe there was some user error or something, but after that I haven’t really used Gemini. I’m curious if people are using Gemini and loving it are u…
This has been my experience too. Gemini might be better for vibe coding or architecture or whatever, but Claude consistently feels better for serious coding. That is, when I know exactly how I want something implemented in a large existing codebase, and I go through the full cycle of implementation, refinement, bug fixing, and testing, guiding the AI along the way.
It also seems to be better at incorporating knowledge from documentation and existing examples when provided.
Re: Gemini 2.5 Flash
#389You can get your HN profile analyzed and roasted by it. It's pretty funny :) https://hn-wrapped.kadoa.com/ I'll add a selection for different models soon.
Didn't expect to be roasted by AI this morning. Nice one
Re: Gemini 2.5 Flash
#390Earlier 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.
Related: Only Claude (to my knowledge) has a desktop app which can directly, and usually quite intelligently, modify files and create repos on your desktop. It's the only "agentic" option among the major players. "Claude, make me an app which will accept Stripe payments and sell an ebook about coding in Python; first create the app, then the ebook." It would take a few passes but Claude could do this; obviously you c…
Maybe I am not understanding something here.
But there are third party options availabe that to the very same thing (e.g. https://aider.chat/ ) which allow you to plug in a model (or even a combination thereof e.g. deepseek as architect and claude as code writer) of your choice.
Therefore the advantage of the model provider providing such a thing doesn't matter, no?