Main
- Posts
- Comments
Discussion
- Posts
- Comments

Stuart_Armstrong comments on 'Dumb' AI observes and manipulates controllers - Less Wrong

33 Post author: Stuart_Armstrong 13 January 2015 01:35PM

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

Article Navigation

CC Licenced

Tags: manipulation superintelligence example learning reinforcement_learning rl reinforcement

Comments (19)

Sort By: Best

You are viewing a single comment's thread. Show more comments above.

Comment author: Stuart_Armstrong 23 July 2015 09:51:26AM 0 points [-]

Actually, you could use corrigibility to get dynamic inconsistency https://intelligence.org/2014/10/18/new-report-corrigibility/ .