factual
Reward Function Specification Is The Real-World Challenge
Games are an efficient AI proving ground partly because reward functions are easy to specify, whereas real-world problems make defining the right objective and reward function in a general yet sufficiently specific way much harder, though even scientific problems usually admit ways to specify the goal.
factualpending
Speaker
Demis HassabisEvidence Quote
“How does one define the right objective function, the right reward function, and the right goals?”
Source
Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold— Dwarkesh Patel PodcastCreated: 6/13/2026, 3:35:13 AM
Your notes
Loading notes...