Post
Max Kleiman-Weiner
maxkw.bsky.social
did:plc:jbopvttj6tmoradsay7qkxj3
LLMs learn beliefs and values from human data, influence our opinions, and then reabsorb those influenced beliefs, feeding them back to users again and again. We call this the "Lock-In Hypothesis" and develop theory, simulations, and empirics to test it in our latest ICML paper!
2025-06-09T20:23:51.450Z