alt Hacker NewsLess than other frontier models. Which is scary honestly.
Replies
qaq • yesterday at 5:07 PM
I have a codex session I am using to vibe code a db thats being going for like 3 month. Still doing OK. Try that in CC.
➕ show 1 reply
Less than other frontier models. Which is scary honestly.
I have a codex session I am using to vibe code a db thats being going for like 3 month. Still doing OK. Try that in CC.
No. GPT models follow instructions significantly better than Claude models.
You tell it too research a repo to find a piece of code it will. Claude will just read the README and guess.