I don’t think this problem bounds capabilities. It just limits the capabilities we can safely teach and the ones we can teach on purpose.
RL agents regularly learn superhuman abilities, they’re just frequently not the one we meant to teach.
I don’t think this problem bounds capabilities. It just limits the capabilities we can safely teach and the ones we can teach on purpose.
RL agents regularly learn superhuman abilities, they’re just frequently not the one we meant to teach.