Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

GPT 5.4 has been the winner this week. Last week Opus 4.6. You can use both in OpenCode.


5.4 kind of falls apart in big/large projects.


How does it compare to using GPT 5.4 inside Codex?


I used Codex for a long time. It's definitely better than Claude Code due to being open source, but opencode is nicer to use. Good hotkeys, plan/build modes, fast and easy model switching, good mcp support. Supports skills, is not the fastest but good enough.


Well not anymore with Claude pro…


It is "not supported" for two month at this point, yet somehow opencode + claude max is still my main workflow today




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: