Comment by tikotus
10 hours ago
Yes! Though I mainly use it for one-shotting full files, so I'm not copying over small diffs. I did try copilot at some point in vscode, but after a week or so I felt like it was slowing me down. Something I knew would be a simple and quick change was now slow since I didn't have enough ownership of the code to do it quickly myself, and prompting for the change took longer than changing it manually if I had had full ownership. So I went back to coding by hand things that aren't a one-shot file.
Thanks for the reply. I'd suggest you improve your workflow with better tooling like Codex or Claude code, and if you have some kind of weird constraint they'll easily follow an AGENTS.md with that.
I too use WebUI version, I prefer friction. I have Claude code extension in VScode but I don't use it much except for making small one time projects.
I refuse to pay any money to these companies specifically AND so far I use it solely for things where copy-pasting is entirely fine.
I used free trial of Claude Code and has not seemed to be superior for my usecases.
Just use opencode/pi/etc with an open weight model?
Just download the ChatGPT app and use the Codex mode.
Using ChatGPT.com for coding tasks has to be a joke in 2026, right? I assumed everyone is using Codex/Claude Code/OpenCode/Pi by now if you’re using these tools.
Yeah! Seems like that's the assumption in this ongoing discussion, so I thought my point of view would be interesting. I'm not saying I'm doing it the right way, possibly I'm being very stupid, but the point here is that it's not just the "normies" who don't know what Sol is.
> it's not just the "normies" who don't know what Sol is.
You are closer to a normie than most here I assume.
No, it's a great point. I think we all live in bubbles and aren't aware of what others around us are doing.
At my admittedly very tiny workplace, I'm the only one who uses agents at all. The rest just use the web interface, though one tried cursor for a bit.
HN vastly over estimate the actual usage of agents, and AI in general. The few times I figure an LLM might help, I just use DuckDuckGos duck.ai.
Lots of large enterprises and organizations have security policies that make it very hard to self-install these tools and haven’t figured out they should add them to their approved software list yet. Federal government in particular is still very slow
I use it for making small disposable scripts, and in-browser chat with copy-pasting output works fine for that.