Agents playing the iterated prisoner's dilemma learn to cooperate. It's usually not a dominant strategy to be entirely sociopathic when other players are involved.

▲

ehnto 11 hours ago | parent [-]

You don't get that many iterations in the real world though, and if one of your first iterations is particularly bad you don't get any more iterations.

▲

cortesoft 9 hours ago | parent [-]

But AI will train in the artificial world

	▲	ehnto 9 hours ago \| parent [-]
		They still fail in the real world, where a single failure can be highly consequential. AI coding is lucky it has early failure modes, pretty low consequence. But I don't see how that looks for an autonomous management agent with arbitrary metrics as goals. Anyone doing AI coding can tell you once an agent gets on the wrong path, it can get very confused and is usually irrecoverable. What does that look like in other contexts? Is restarting the process from scratch even possible in other types of work, or is that unique to only some kinds of work?