You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

Manfred comments on [MIRIx Cambridge MA] Limiting resource allocation with bounded utility functions and conceptual uncertainty - Less Wrong Discussion

4 Post author: Vika 02 October 2014 10:48PM

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

Comments (28)

You are viewing a single comment's thread.

Comment author: Manfred 03 October 2014 12:45:21AM 2 points [-]

Hm. For cases where the utility function really is an exponential sigmoid, though, the resources devoted to the central hypothesis growing sublinearly in total resources actually seems like a good idea.