News for hackers. Stuff that matters.

A comment on Google Scholar search: "certainly, here is" -chatgpt -llm. Parent comment

Re:Google Scholar search: "certainly, here is" -chatgpt -llm by dougb5 on Sunday March 17, 2024 @01:13PM (#39736017)
My guess is that ChatGPT does it because RLHF rewards strongly stated opinions, because that's what humans prefer. It's a kind of "sycophantic behavior" that researchers have observed in these models (https://arxiv.org/abs/2310.13548)
[ Parent | on HN ]

There are no comments on this comment yet.