LessWrong (Curated & Popular) cover image

"AGI Ruin: A List of Lethalities" by Eliezer Yudkowsky

LessWrong (Curated & Popular)

00:00

Is the a G I Planning to Kill Us?

Even if we did know what was going on inside the giant inscrutable matreces, while the a g i was still too weak to kill us, this would just result in us dying with more dignity. When you explicitly optimize against a detector of unalligned thoughts, you're partially optimizing for more alligned thoughts and partiallyopti sing for unlined thoughts that are harder to detect. Optimizing against an interpreted thought optimizes against interpretability. We cannot mentally check all the ities it examines, and we cannot see all the consequences of its outputs using our own mental talent. Any pivotal act that is not something we can go do right now will take advantage of the a g

Play episode from 42:32
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app