ai-internal-state

#ai-internal-state

@Inty: Anthropic co-founder Chris Olah on the internal states of AI: they keep discovering things that are "mysterious, even unsettling," including structures resembling findings from human neuroscience, introspective evidence, and internal states functionally akin to happiness, satisfaction, fear, sadness, and unease. Olah says he doesn’t know what this means, but believes it warrants continued, careful scrutiny.

X AI KOLs Timeline ↗ · 2026-05-25 Cached

Anthropic co-founder Chris Olah discusses findings on the internal states of AI, including structures similar to human neuroscience results and introspective evidence. He finds these discoveries mysterious and unsettling, and believes they merit cautious and ongoing analysis.

0 favorites 0 likes

ai-internal-state

Submit Feedback