Prof. Kangwook Lee: no SC/SC2 agent hits semi-pro level under hard API limits without micro-cheating
Kangwook_Lee · x · 2026-09-26
AI researcher Kangwook Lee (professor at UW-Madison) argues that there is still no evidence of any model playing SC/SC2 at decent semi-pro level under hard API limits, behavior-cloned bootstrapped or not.
- In his view, both AlphaStar and the recent agent heavily rely on micro-cheating (exploiting API-level advantages over human micro).
- Responding to the point that AlphaStar was bootstrapped via human behavior cloning while the new one wasn't, he holds the objection stands regardless.
- He remains open-minded: if 10x compute made it work, he'd love to see it — but current evidence doesn't support it.
Related event: Debate Erupts Over Fully Self-Trained StarCraft AI as AGI Benchmark(5 posts)→
More from Models
- Running DeepSeek 4.1 locally on an $800 rig with a used RTX 3090 at 2-3 tok/s — LankyGuitar6528 · 2026-11-11
- Google open-sources Harness², an agent that rewrites its own setup per task — Arindam_1729 · 2026-11-11
- Dev dumps Codex desktop app over quality issues, falls back to codex-cli — tekbog · 2026-11-11
- Why do old models get dumber before launches? Lab party, says joking X post — glcst · 2026-11-11
- Grok Bot now detects hidden prompt injections, warns users and refuses to follow them — XFreeze · 2026-11-11
- Shanghai Institute Open-Sources Nex-N2.6, a 321B Multimodal Agentic Model — victormustar · 2026-11-11