Comment by codazoda
1 day ago
Since you were forced, are you getting good results from them?
I’ve experimented, and I like them when I’m on an airplane or away from wifi, but they don’t work anywhere near as well as Claude code, Codex CLI, or Gemini CLI.
Then again, I haven’t found a workable CLI with tool and MCP support that I could use in the same way.
Edit: I was also trying local models I could run on my own MacBook Air. Those are a lot more limited than something like a larger Llama3 in some cloud provider. I hadn’t done that yet.
For writing decent code, absolutely not, maybe a simple bash script or the obscure flags to a command that I only need to run once and couldn't be bothered to google or look through the man page etc. I'm using smaller models for less coding related stuff.
Thankfully OpenAI hasn't blocked me yet and I can still use Codex CLI. I don't think you're ever going to see that level of power locally (I very much hope to be wrong about that). I will move over to using a cloud provider with a large gpt-oss model or whatever is the current leader at the time if/when my OpenAI account gets blocked for no reason.
The M-series chips in Macs are crazy, if you have the available memory you can do some cool things with some models, just don't be expecting to one shot a complete web app etc.