Self-play systems (OpenAI Five in Dota, hide-and-seek agents, AlphaZero) produce creative solutions that surprise researchers with truly novel strategies not anticipated during design, which is an important property for AGI that current supervised learning systems routinely lack.
factualpending
Speaker
Ilya SutskeverEvidence Quote
“pretty much every self-play system both are dotabot i don't know if openai had a release about multi-agent where you had two little agents who were playing hide and seek and of course also alpha zero they were all surprising behaviors they all produce behaviors that we didn't expect they are creative solutions to problems”
Created: 8/10/2026, 10:49:52 PM
Your notes
Loading notes...