Bonus: Preventing an AI-Related Catastrophe
Hear This Idea
00:00
AI Safety
There are some reasons to think that the core argument that any advanced strategically aware planning system will buy default seek power isn't totally right. Not all misaligned power-seeking behaviour seems like it will actually disempower all of humanity. Disempowering all of humanity appears to be a particularly robust way to ensure that AI systems will always be able to achieve their goals. For more on this example, see page 25 of Garfinkel's review of Karlsmith's report.
Transcript
Play full episode
