Larifari comments on Size of the smallest recursively self-improving AI? - Less Wrong

4 Post author: alexflint 30 March 2011 11:31PM

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

Comments (47)

You are viewing a single comment's thread.

Comment author: Larifari 31 March 2011 11:27:33AM 4 points [-]

Even a FOOM seed only a few hundred bytes would not necessarily have been produced by evolution - there are 2^800 different possibilities for a 100-byte snippet. Only if there are intermediate steps in increasing complexity and fitness, evolution can find a solution in such a large search space. If the shortest possible seed is completely isolated in the search space, there is no way it can be found, neither by evolution nor by deliberate optimization.

Comment author: timtyler 31 March 2011 05:32:44PM 1 point [-]

Be careful with saying something is impossible. Maybe that large seach space can be cut down to size by proofs or clever algorithms.