I don't like Javascript for CLI. I think OpenAI did the right thing by switching to Rust.
5 Things to Try with Gemini 3 Pro in Gemini CLI
11–20 of 48 posts
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#12Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
model provider CLIs are a trap, less freedom of choice, less privacy, way more prohibitions buried in the fine print
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#13Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
make a cli router like openrouter that just accepts your args and passes them to whichvever one is leading at the moment? could be fun.
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#14Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
I haven't tried Gemini CLI with Gemini 3 Pro, but pretty much all the others. I usually run four agents at the same time, for each task, giving them the same prompt and then comparing their responses.
Gemini CLI has the lowest rate limits, lowest inability to steer the models (not sure that's a model or tooling thing, but I cannot get any of the Google models to stop outputting code comments constantly and everywhere) and seemingly the API frequently becomes unavailable for some reason.
Claude Code is fast, easy to steer, but the quality really degrades really quickly and randomly, seemingly by time of day. I'm not sure if they're running differently quanitized models during different times, but there is a clear quality difference depending on when in the day I use it, strangely. Haven't found a way of verifying this though, ideas welcome.
Codex CLI is probably what I use the most, with "gpt-5+high", which is kind of slow, a lot slower than Claude Code, but it almost always gets it right on the first try, and seemingly no other model+tool does instruction following as good, even if your AGENTS.md is almost overflowing with rules and requirements, it seems to nail things anyways.
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#15Correct me if I'm wrong, but in this demo video of the user instructing the model to use `git bisect` to find a commit ( https://storage.googleapis.com/gweb-developer-goog-blog-asse... ), doesn't this actually showcase a big issue with today's models? In the end, the model only ran `git bisect` (if we're to believe the video at least) for various pointless reasons, it isn't being used for what it's usually used for.…
Looks right to me. At t=0:50 it shows other git bisect commands being run. The git biset reset at the end is ending bisection as it's complete. Video is really a terrible format for terminal demos, you've got to pause it as the screen flashes text faster than you can read...
> Looks right to me. At t=0:50 it shows other git bisect commands being run. The git biset reset at the end is ending bisection as it's complete.
But what is that actually doing? It looks like when it's running the git bisect, it already knows what the commit is, and could have just returned it. The only reason it ran any bisecting at all, was because the user (erroneously) asked it specifically to use git bisect. It didn't have to.
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#16Wow, so excited to try!
> gemini
It seems like you don't have access to Gemini 3. Learn more at https://goo.gle/enable-preview-features To disable Gemini 3, disable "Preview features" in /settings. • 1. Switch to gemini-2.5-pro • 2. Stop Note: You can always use /model to select a different option.
Google never disappoints with their half-ass-launches.
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#17Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
I think the TUI agents are pretty similar; I can use CC, Codex, Gemini, and opencode interchangeably.
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#18Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
Maybe these new releases bring some serious enhancements, but my experience with the Gemini cli has been dreadful. It craps out at least half of the time. When it works it is ridiculously fast so I keep trying it. But it has proven very inferior to the Claude code experience in my usage
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#19Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
I haven't tried Gemini CLI with Gemini 3 Pro, but pretty much all the others. I usually run four agents at the same time, for each task, giving them the same prompt and then comparing their responses. Gemini CLI has the lowest rate limits, lowest inability to steer the models (not sure that's a model or tooling thing, but I cannot get any of the Google models to stop outputting code comments constantly and everywhere…
Codex has gotten kind of nerfed with their weird choice to limit loc read to 250 and dropping middle of context a lot. None of the CLIs are performing well for me right now. I'm codex and claude max btw. Disappointing.
Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI
#20Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude…
Codex with gpt-5-high I trust to get things right without much effort. Claude is the best tool using agent out there. Very good at using the tools to ground whether changes are producing outcomes.