Eugine_Nier comments on Rationality Quotes August 2012 - Less Wrong

6 Post author: Alejandro1 03 August 2012 03:33PM

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

Comments (426)

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

Comment author: Eugine_Nier 28 August 2012 02:57:03AM *  1 point [-]

Even if the AI can modify its code, it can't really do anything that wasn't entailed by its original programming.

The hard part is predicting everything that was entailed by its initial programing and making sure it's all safe.

Comment author: V_V 28 August 2012 10:39:47AM 2 points [-]

That's right, history of engineering tells us that "provably safe" and "provably secure" systems fail in unanticipated ways.