AI Safety Public Materials

Edited by Thane Ruthenis last updated 26th Aug 2022

AI Safety Public Materials are posts optimized for conveying information on AI Risk to audiences outside the AI Alignment community — be they ML specialists, policy-makers, or the general public.

Posts tagged AI Safety Public Materials

129AGI safety from first principles: Introduction

Ω

Richard_Ngo

5y

Ω

18

241Slow motion videos as AI risk intuition pumps

Andrew_Critch

3y

41

32DL towards the unaligned Recursive Self-Optimization attractor

jacob_cannell

4y

22

105A transcript of the TED talk by Eliezer Yudkowsky

Mikhail Samin

2y

13

212An AI risk argument that resonates with NYTimes readers

Julian Bradshaw

3y

14

124When discussing AI risks, talk about capabilities, not intelligence

Ω

Vika

2y

Ω

7

59AISafety.info "How can I help?" FAQ

steven0461, Severin T. Seehrich

2y

0

33The Importance of AI Alignment, explained in 5 points

Ω

Daniel_Eth

3y

Ω

2

7Mati's introduction to pausing giant AI experiments

Mati_Roy

2y

0

21Uncontrollable AI as an Existential Risk

Karl von Wendt

3y

0

20AI Safety Arguments: An Interactive Guide

Lukas Trötzmüller

3y

0

17Distribution Shifts and The Importance of AI Safety

3y

2

2y

10

120Stampy's AI Safety Info soft launch

steven0461, Robert Miles

2y

9

115“The Era of Experience” has an unsolved technical alignment problem

Ω

Steven Byrnes

5mo

Ω

48

LESSWRONG
LW

LESSWRONG
LW

AI Safety Public Materials