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.

▲

wasabi991011 16 days ago | parent | next [-]

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

▲

boxed 16 days ago | parent | prev [-]

Less than other frontier models. Which is scary honestly.

▲

impulser_ 16 days ago | parent | next [-]

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.

▲

qaq 16 days ago | parent | prev [-]

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.

	▲	ishurand4 16 days ago \| parent [-]
		What's the token usage at?