Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
00:00
The Drive Towards Self-Preservation in AIs
Human failure modes are different from the failure modes of AIs so humans will not fail as often in issues of common sense for example. So why would AIs develop drives towards self-preservation or will they? It seems like from evolutionary terms game theoretic terms you must if you don't you simply get out competed by agents which do if you not around to complete your goals you by definition cannot complete your goals. If you want to bring in a cup of coffee you have to be turned on you have to existYou have to be available to make those things happen.
Transcript
Play full episode
