whpearson comments on Open Thread: February 2010 - Less Wrong
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 (738)
Backprop is likely to be safe. Lots of AI students play around with it and it is well behaved mathematically. If it was going to kill us it would have done so already. More advanced stuff has to be evaluated individually.