Scientific research and proof-reading. Gemini is the laziest LLM I've used. Frequently he will lie that he searched for something and just make stuff up, basically never happens to me when I'm using gpt5.2.
The way I summed it up to a friend recently is that Gemini 3 is smarter but Grok 4 works harder. Very loose approximation, but roughly maps to my experience. Both are extremely useful (as is GPT-5.2), but I use them on different tasks and sometimes need to manage them a bit differently.
Gemini loves to ignore Gemini.md instructions from the first minutes, to replace half of the python script with "# other code...", or to try to delete files OUTSIDE of the project directory, then apologise profusely, and try it again.
Utterly unreliable. I get better results, faster, editing parts of the code with Claude in a web ui, lol.
Any coding task produces some trash, while I can prototype with ChatGPT quite a lot, sometimes delivering the entire app almost entirely vibe-coded. Gemini, it takes a few prompts for it to get me mad and just close the tab. I use only the free web versions, never agentic ‘mess with my files’ thing. Claude, is even better than that, but I keep it for serious tasks only, so good it is.
Scientific research and proof-reading. Gemini is the laziest LLM I've used. Frequently he will lie that he searched for something and just make stuff up, basically never happens to me when I'm using gpt5.2.
The way I summed it up to a friend recently is that Gemini 3 is smarter but Grok 4 works harder. Very loose approximation, but roughly maps to my experience. Both are extremely useful (as is GPT-5.2), but I use them on different tasks and sometimes need to manage them a bit differently.
Do you use it directly? I've only used it though Kagi Assistant but it works better than any other model for me
Yes, only directly (I mean through the default gemini interface, not API).
Gemini loves to ignore Gemini.md instructions from the first minutes, to replace half of the python script with "# other code...", or to try to delete files OUTSIDE of the project directory, then apologise profusely, and try it again.
Utterly unreliable. I get better results, faster, editing parts of the code with Claude in a web ui, lol.
Any coding task produces some trash, while I can prototype with ChatGPT quite a lot, sometimes delivering the entire app almost entirely vibe-coded. Gemini, it takes a few prompts for it to get me mad and just close the tab. I use only the free web versions, never agentic ‘mess with my files’ thing. Claude, is even better than that, but I keep it for serious tasks only, so good it is.
In my experience with Gemini, I find it incapable of not hallucinating.