News for hackers. Stuff that matters.
Re:GPT‑5.4 Mini and Nano by tom1337 on Tuesday March 17, 2026 @02:53PM (#47416647)
Yea absolutely. I am using GPT 5.2 / 5.2 Codex with OpenCode and it just doesn't get what I am doing or looses context. Claude on the other side (via GitHub Copilot) has no problem and also discovers the repository on it's own in new sessions while I need to basically spoonfeed GPT. I also agree on the speed. Earlier today I tasked GPT 5.2 Codex with a small refactor of a task in our codebase with reasoning to high and it took 20 minutes to move around 20 files.
Re:GPT‑5.4 Mini and Nano by furyofantares on Tuesday March 17, 2026 @03:03PM (#47416774)
I don't know any reason to use 5.2, when 5.3 is quite a bit faster.
Re:GPT‑5.4 Mini and Nano by spiderfarmer on Tuesday March 17, 2026 @03:05PM (#47416798)
If using OpenAI models, use the Codex desktop app, it runs circles around OpenCode.
Re:GPT‑5.4 Mini and Nano by qaz_plm on Tuesday March 17, 2026 @06:57PM (#47419503)
Can you educate me as to what makes Codex app superior using the same GPT model in both? Thx in advance!
Re:GPT‑5.4 Mini and Nano by stavros on Tuesday March 17, 2026 @11:41PM (#47421390)
Usually it's the prompts, or the model is tuned to the specific first-party tools. Sometimes that gives an edge over the generic tools, unfortunately.
Re:GPT‑5.4 Mini and Nano by spiderfarmer on Wednesday March 18, 2026 @03:49AM (#47422813)
It's the harness.