GPT-5.6 - Hackdot

Re:GPT-5.6 by mattmanser on Thursday July 09, 2026 @01:53PM (#48849895)

Last time I used Codex it would make loads of assumptions, often quite big ones, without asking.

Did they fix that, as that for me was what actually made codex worse.

[ Parent | on HN ]

Re:GPT-5.6 by arcanemachiner on Thursday July 09, 2026 @02:24PM (#48850326)

I find that I have to tell GPT and Claude to keep asking me questions, or they will just fill in the gaps themselves (wrongly).

[ Parent | on HN ]

Re:GPT-5.6 by dboreham on Friday July 10, 2026 @10:17PM (#48867955)

My experience has been that Claude/Opus will ask me questions, although sometimes I have to step in and redirect a bit. Codex/GPT just dives in and cranks code out, which after using Claude for a year I found rather concerning. It wrote working code though. Claude/Fable does something similar (asks far fewer questions than Opus) fwiw.

[ Parent | on HN ]

Re:GPT-5.6 by nico1207 on Thursday July 09, 2026 @02:46PM (#48850621)

Did you use plan mode?

[ Parent | on HN ]