LESSWRONG

Dewey 2011 lays out the rules for one kind of agent with a mutable value system. The agent has some distribution over utility functions, whi

Epistemic status: Trying to air out some thoughts for feedback, we'll see how successfully. May require some machine learning to make sense,

Discussion article for the meetup : Urbana-Champaign: Quorum for discourse WHEN: 06 September 2015 02:00:00PM (-0500) WHERE: Altgel

Epistemic status: One part quotes (informative, accurate), one part speculation (not so accurate). One avenue towards AI safety is the con

[This post borders on some well-trodden ground in information theory and machine learning, so ideas in this post have an above-average chanc

One question I've had recently is "Are agents acting on selfish preferences doomed to having conflicts with other versions of themselves?" A

I When preferences are selfless, anthropic problems are easily solved by a change of perspective. For example, if we do a Sleeping Beauty

Strongly related: the Ebborians Imagine mapping my brain into two interpenetrating networks. For each brain cell, half of it goes to one m

Discussion article for the meetup : Urbana-Champaign: Finishing Up WHEN: 14 December 2014 02:00:00PM (-0600) WHERE: 206 S. Cedar St

Discussion article for the meetup : Urbana-Champaign: Seeking advice WHEN: 30 November 2014 02:00:00PM (-0600) WHERE: 206 S. Cedar