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

Will_Pearson comments on That Alien Message - Less Wrong

111 Post author: Eliezer_Yudkowsky 22 May 2008 05:55AM

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

Comments (164)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Will_Pearson 22 May 2008 08:08:17PM 0 points [-]

Proof of concept does not require a full AI, I was merely talking about showing how powerful limited versions of solmonoff induction are. Considering you are saying that that is the epitome of information efficiency.

Unless that is considered playing with dynamite as well. Have you asked that people stop playing with levin and other universal searchers?

I have my doubts that thinking simple is always best. How much data (and what type) would you require to assume that there is another learning system in the environment. Humans have that bias and apply it too much (Zeus, Thor), but generally learners are not simple. In order to predict a learning system, you have to have the starting state, the algorithm and the environmental interaction that caused the learner to be have the beliefs it has had, rather than just trying to predict the behaviour.

If you consider the epitome of learners to be solomonoff inducers, whose behaviour can be unboundedly complex, you should expect other learners to aspire to unbounded complexity. Without a bias like this I think you will spend a long time thinking that humans are simpler than they actually are.