▲ | GPT‑5-Codex and upgrades to Codex(simonwillison.net) | ||||||||||||||||||||||
55 points by amrrs 20 hours ago | 11 comments | |||||||||||||||||||||||
▲ | pietz 3 hours ago | parent | next [-] | ||||||||||||||||||||||
Do we really know that gpt-5-codex is a finetune of gpt-5(-thinking)? The article doesn't clearly say that, right? I suspect that this is smaller than gpt-5 or at least a quantized version. Similar to what I suspect Opus 4.1 is. That would also explain why it's faster. | |||||||||||||||||||||||
| |||||||||||||||||||||||
▲ | knowsuchagency 13 hours ago | parent | prev | next [-] | ||||||||||||||||||||||
It's annoying to see a link to a Theo video -- same guy who went with Simon to OpenAI's GPT-5 glazefest and had to backpedal when everyone realized what a shill he is. I know neither of them are journalists -- I'm probably expecting too much -- but Simon should know better. | |||||||||||||||||||||||
| |||||||||||||||||||||||
▲ | sanxiyn 14 hours ago | parent | prev | next [-] | ||||||||||||||||||||||
> "We find that comments by GPT‑5-Codex are less likely to be incorrect or unimportant" -- less unimportant comments in code is definitely an improvement! This seems to be a misunderstanding. In the original OpenAI article, comment here is about code review comment, not comment in code. | |||||||||||||||||||||||
▲ | lostmsu 17 hours ago | parent | prev | next [-] | ||||||||||||||||||||||
The pelican is not very good | |||||||||||||||||||||||
| |||||||||||||||||||||||
▲ | ath3nd 17 hours ago | parent | prev [-] | ||||||||||||||||||||||
[dead] |