Since these latter approaches require new work and investment that might fail with unknown probability, they are low-confidence.
This issue in Benefits allocation resembles a multi-armed bandit problem, suggesting that that field of literature should be useful.
Except in multi arm bandit problems, none of the leavers blow the whole bandit up. Careless exploration of novel agent designs is an X risk.
I agree that that is true for AGI systems.
Except in multi arm bandit problems, none of the leavers blow the whole bandit up. Careless exploration of novel agent designs is an X risk.
I agree that that is true for AGI systems.