That's the flip side of the same symptom. One model is instructed to agree with ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		paxys 40 days ago \| parent \| context \| favorite \| on: The Case That A.I. Is Thinking That's the flip side of the same symptom. One model is instructed to agree with the user no matter what, and the other is instructed to stick to its guns no matter what. Neither of them is actually thinking.

ACCount37 39 days ago [–]

Wrong. The same exact model can do both, depending on the circumstances.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact