Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

whpearson comments on AI safety: three human problems and one AI issue - Less Wrong Discussion

6 Post author: Stuart_Armstrong 19 May 2017 10:48AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (6)

You are viewing a single comment's thread.

Comment author: whpearson 19 May 2017 04:08:06PM 0 points [-]

Also I think there are other problem sets if physics is such that AI hits a limit for a while and is only very powerful rather than stupidly powerful. E.g. not powerful enough to takeover the whole world but powerful enough to destroy the whole world.

Then you have to deal with potential communities of AIs and their dynamics. Which might fit into poor predictions (but is magnified by having a multiplicity of AI).