StarCraft AI trained purely by self-play sparks AGI benchmark debate
syhw · x · 2026-09-26
A debate over whether the StarCraft AI counts as an AGI benchmark. Proponents note it was trained from scratch purely via self-play with zero human data, and argue that capping APM (500 peak / 300 average) and adding 10x more compute would make it even stronger. Skeptic syhw — a competitive StarCraft player who did PhD-level research on the game — counters that not having to move the screen is effectively cheating, and piling on more constraints (eat, drink, sleep?) would strip the benchmark of meaning. Bottom line: this is not an AGI benchmark. The core dispute: what superhuman self-play without human data actually proves, and how faithfully agent benchmarks must simulate real interaction.
Related event: Self-Play StarCraft AI Sparks AGI Benchmark Debate(4 posts)→
More from AGI Musings
- China overtakes US as top workplace for elite AI researchers, hiring 41% vs 34% — pstAsiatech · 2026-09-26
- OpenAI researcher questions EA's core axiom: is suffering actually bad? — willdepue · 2026-09-26
- The more time you spend with agents, the lower your tolerance for mistakes — justalexoki · 2026-09-26
- WSJ: AI has become the biggest economic bet in US history — xiaosun86 · 2026-09-26
- Ribbonfarm's vgr turns 17 years of writing into a paid AI replica of his mind — sebpaquet · 2026-09-26
- Cardiologist on AI in healthcare: "bots fighting bots, a dystopia nobody wants" — MannyKayy · 2026-09-26