Karpathy: LLMs Lack Cultural Accumulation and Self-Play

i_dg23 · x · 2026-08-01

Andrej Karpathy highlighted that current Large Language Models (LLMs) are missing two critical elements that propelled human intelligence: cultural accumulation and self-play.

Researcher Noah added that self-play works well in chess, Go, and poker because they are two-player zero-sum games, which simplifies the problem. The real world is much messier, which is why we haven't seen many self-play successes in LLMs yet.

Related event: Karpathy: LLMs Lack Cultural Accumulation and Self-Play(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →