Well the big labs certainly haven't intentionally tried to train away this emerg... | Hacker News

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

		gradus_ad 21 days ago \| parent \| context \| favorite \| on: Sycophancy is the first LLM "dark pattern" Well the big labs certainly haven't intentionally tried to train away this emergent property... Not sure how "hey let's make the model disagree with the user more" would go over with leadership. Customer is always right, right?

htrp 21 days ago [–]

The problem is asking for user preference leads to sycophantic responses

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