Six Dimensions of Operational Adequacy in AGI Projects — LessWrong

Editor's note:  The following is a lightly edited copy of a document written by Eliezer Yudkowsky in November 2017. Since this is a snapshot of Eliez…
Editor's note:  The following is a lightly edited copy of a document written by Eliezer Yudkowsky in November 2017. Since this is a snapshot of Eliez…

25 of Eliezer Yudkowsky Podcasts Interviews

AI Safety is Dropping the Ball on Clown Attacks — LessWrong

Embedded World-Models - Machine Intelligence Research Institute

MIRI announces new Death With Dignity strategy - LessWrong 2.0

Ideas for AI labs: Reading list — LessWrong

We don't need AGI for an amazing future — LessWrong

Embedded World-Models - Machine Intelligence Research Institute

Review Voting — AI Alignment Forum

Auditing large language models: a three-layered approach

PDF) On Controllability of AI