Self-Play Game AI Trained From Scratch Is 'The Game', Says Researcher; 10x Compute Would Make It Even Better

syhw · x · 2026-09-26

Researcher syhw argues a game AI trained purely via self-play from scratch, with no human data, proves the approach works — and predicts that capping it at human-like APM (500 peak / 300 average) with 10x more compute would yield an even stronger agent.

Related event: Self-play game AI sparks debate over scaling and AGI benchmark status(4 posts)→

Original post →

More from Research

Research channel →