Which Gpt model and reasoning level did you use in Codex and Amp? Generally I ha... | Hacker News

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

		sumedh 10 days ago \| parent \| context \| favorite \| on: Unrolling the Codex agent loop Which Gpt model and reasoning level did you use in Codex and Amp? Generally I have noticed Gpt 5.2 codex is slower compared to Sonnet 4.5 in Claude Code.

nl 10 days ago [–]

Amp doesn't have a conventional model selector - you choose fast vs smart (I think that's what it is called).

In smart mode it explores with Gemini Flash and writes with Opus.

Opus is roughly the same speed as Codex, depending on thinking settings.

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