Jiro comments on xkcd on the AI box experiment - Less Wrong Discussion
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (229)
Eliezer has done (2) many times.
Eliezer has denied that the exact Basilisk scenario is a danger, but not that anything like it can be a danger. He seems to think that discussing acausal trade with future AIs can be dangerous enough that we shouldn't talk about the details.