reward problem
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Jul 17, 2025 by Misha Laskin · across every show →
Everything said about reward problem, oldest first
Jul 17, 2025
Laskin: Accurately verifying arbitrary outcomes is ASI-complete
“The reward problem in itself is at the time I called, I thought it was AGI complete. Now I'd say it's ASI complete, but by the time you have a neural network that can accurately verify any outcome, that is probably a super intelligence.”