LessWrong Sequence Posts Discussed in this Episode:
on hiatus, returning this summer
245 – AI Welfare, with Rob Long and Rosie Campbell of Eleos
The Bayesian Conspiracy
00:00
Self-Reports and Their Limitations
They explain why LLM self-reports are unreliable, sensitive to prompting, and shaped by training and safety guidelines.
Play episode from 24:17
Transcript
