/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 www.greaterwrong.com
Policy Debates Should Not Appear One-Sided - LessWrong 2.0 viewer
| | esr.ibiblio.org
Responding to Eliezer Yudkowsky's "Overcoming Bias" - Armed and Dangerous
5.9 parsecs away

Travel
| |
| | backreaction.blogspot.com
Sabine Hossenfelder: Backreaction: 10 Misconceptions about Free Will
6.0 parsecs away

Travel
| | Science News, Physics, Science, Philosophy, Philosophy of Science
| | www.alignmentforum.org
Coherent behaviour in the real world is an incoherent concept - AI Alignment Forum
6.1 parsecs away

Travel
| | Note: after putting this online, I noticed several problems with my original framing of the arguments. While I don't think they invalidated the overa...
| | www.greaterwrong.com
The Open Agency Model - LessWrong 2.0 viewer
25.1 parsecs away

Travel
| Eric DrexlerCentre for the Governance of AIUniversity of Oxford This document argues for "open agencies" - not opaque, unitary agents - as the appropriate model for applying future AI capabilities to consequential tasks that call for combining human guidance with delegation of planning and implementation to AI systems. This prospect reframes and can help to tame a wide range of classic AI safety challenges, leveraging alignment techniques in a relatively fault-tolerant context.