Aligning AGI to human values is a question about training a value function (objective/goal) that is learned separately from the agent's main capability function, similar to how humans have internal rather than external reward functions that they can choose to change.
definitionpending
Speaker
Ilya SutskeverEvidence Quote
“it would be a question about how to get an rl agent that's optimizing a value function which itself is learned and if you look at humans humans are like that because the reward function the value function of humans is not external it is internal”
Created: 8/10/2026, 10:49:52 PM
Your notes
Loading notes...