undefined | Better HN

0 pointsimpulser_1d ago0 comments

Crazy they bring up honest, when Claude models are literally known for straight up lying about things it has done and tries to act like it did what you asked.

0 comments

wasabi9910111d ago

Which is why they brought it up as something they are trying to improve.

boxed1d ago

Less than other frontier models. Which is scary honestly.

impulser_OP1d ago

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.

qaq1d ago

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.

ishurand41d ago

What's the token usage at?

j / k navigate · click thread line to collapse