Eliezer Yudkowsky: The Most Important Thinker Of Our Time

Video Description

Eliezer Yudkowsky is the founder of the AI safety field, and in my opinion, the most important thinker of our time. 00:00:00 — Eliezer Yudkowsky Intro 00:01:25 — Recent validation of Eliezer's ideas 00:03:46 — Sh*t now getting real 00:08:47 — Eliezer’s rationality teachings 00:10:39 — Rationality Lesson 1: I am a brain 00:13:10 — Rationality Lesson 2: Philosophy can reduce to AI engineering 00:17:19 — Rationality Lesson 3: What is evidence 00:22:41 — Rationality Lesson 4: Be more specific 00:28:34 — Specificity as a superpower in debates 00:30:19 — Rationality Lesson 5: How to spot a rationalization 00:36:52 — Rationality might upend your deepest expectations 00:38:18 — The typical reaction to superintelligence risk 00:40:07 — Eliezer is a techno-optimist, with a few exceptions 00:47:57 — Why AI is an existential risk 00:53:24 — Engineering outperforms biology 01:02:09 — The threshold of "supercritical" AI 01:13:23 — How to convince people there's a discontinuity ahead 01:18:06 — The alignment problem: Are current AI systems aligned? 01:28:20 — AI alignment researchers as overconfident alchemists 01:37:52 — The strawberry Xerox test for alignment 01:41:25 — What would a good scenario look like? 01:57:22 — Can we keep “narrow AI” safe? 02:04:48 — Eliezer's proposal for international coordination on AI 02:12:02 — AI companies don’t get why alignment is hard 02:18:32 — Ideal impact of If Anyone Builds It, Everyone Dies 02:24:24 — Wrap-up & how to support Eliezer's efforts Transcript: https://www.lesswrong.com/posts/kiNbFKcKoNQKdgTp8/interview-with-eliezer-yudkowsky-on-rationality-and --- Please watch my other show too: @DoomDebates I debate famous people about whether Eliezer Yudkowsky's ideas are correct. My previous guests include Vitalik Buterin, Rob Miles, Gary Marcus, and Mike Israetel. “Good work!“ —Eliezer Yudkowsky --- Credit to Dagan Shani (@DaganOnAI ) for the Eliezer Yudkowsky intro reel!