A thread through the archive

Blue-Minimizing Robot

Essays tagged “Blue-Minimizing Robot”. Follow an idea across the archive.

Essays on Blue-Minimizing Robot

2 essays

Jul 15, 2011LW

To what degree do we have goals?

Scott argues against negotiating with unconscious desires, distinguishing between behavior-executors (which have context-dependent urges) and utility-maximizers (which have stable preferences), and suggests we mistakenly model ourselves as the latter when we're actually the former.

13 min read 1,971 words

Jul 4, 2011LW

The Blue-Minimizing Robot

Scott uses a thought experiment about a robot that shoots blue things to argue that we mistakenly interpret simple programmed behaviors as goal-directed utility maximization, when really the robot is just executing code, not minimizing blue.

8 min read 1,108 words

AI goals Anna Salamon behavior-executor vs utility-maximizer