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)→
More from Research
- Lawrence Krauss podcast asks whether AI will supercharge scientific paper mills — willcb · 2026-09-26
- Framework-free prototype learner lets local LLMs learn corrections instantly, no fine-tuning — thisdudelikesAI · 2026-09-26
- Building an eval harness for ChatGPT, and the contamination problem of seen solutions — tak3sh8 · 2026-09-26
- Maximize intelligence per flop: decay adaptivity to trade for precision — willcb · 2026-09-26
- Why specialized agents that update their own weights beat generalist models — willcb · 2026-09-26
- Project Callisto: Nine Years and 500 Samples Find No Evidence of Cold Fusion — skdh · 2026-09-26