Re:GPT-5.3-Codex
by nerdsniper on Thursday February 05, 2026 @02:40PM
(#46904049)
Opus 4.5 still worked better for most of my work, which is generally "weird stuff". A lot of my programming involves concepts that are a bit brain-melting for LLMs, because multiple "99% of the time, assumption X is correct" are reversed for my project. I think Opus does better at not falling into those traps. Excited to try out 5.3
[ Parent
| on HN ]
what do you do?
Re:GPT-5.3-Codex
by audience_mem on Thursday February 05, 2026 @06:51PM
(#46907139)
He works on brain-melting stuff, the understanding of which is far beyond us.
Re:GPT-5.3-Codex
by nerdsniper on Friday February 06, 2026 @04:10AM
(#46910653)
It's relatively easy for people to grok, if a bit niche. Just sometimes confuses LLMs. Humans are much better at holding space for rare exceptions to usual rules than LLMs are.