GPT-5.3-Codex - Hackdot

Re:GPT-5.3-Codex by smith7018 on Thursday February 05, 2026 @02:28PM (#46903909)

I just asked Opus 4.6 to debug a bug in my current changes and it went for 20 minutes before I interrupted it. Take that as you will.

[ Parent | on HN ]

Re:GPT-5.3-Codex by bgirard on Thursday February 05, 2026 @02:58PM (#46904329)

Doesn't feel like a useful data point without more context. For some hard bugs I'd be thrilled to wait 30 minutes for a fix, for a trivial CSS fix not so much. I've spent weeks+ of my career fix single bugs. Context is everything.

[ Parent | on HN ]

Re:GPT-5.3-Codex by smith7018 on Thursday February 05, 2026 @03:21PM (#46904659)

Sure, but I've never experienced a 20 minute wait with CC before. It was an architectural question but it would have taken a couple minutes with a definitive answer on 4.5.

[ Parent | on HN ]

Re:GPT-5.3-Codex by sejje on Friday February 06, 2026 @02:11PM (#46916858)

> I've spent weeks+ of my career fix single bugs.

Same, same. It's not a useful data point at all.

bug: llm alignment

timeframe to fix : probably never

[ Parent | on HN ]

Re:GPT-5.3-Codex by mrcwinn on Thursday February 05, 2026 @11:33PM (#46909161)

As they point out in their blog post, 4.6 intentionally thinks longer, but you can adjust it from the CLI.

[ Parent | on HN ]