Building the field of AI safety

TagLast edit: 28 Oct 2022 15:56 UTC by Lizka

Building the field of AI safety refers to the family of interventions aimed at growing, shaping or otherwise improving AI safety as an intellectual community.

Announcing the Cambridge Boston Alignment Initiative [Hiring!]

kuhanj2 Dec 2022 1:07 UTC

83 points

0 comments1 min readEA link

There should be a public adversarial collaboration on AI x-risk

pradyuprasad23 Jan 2023 4:09 UTC

56 points

5 comments2 min readEA link

Announcing the AI Safety Field Building Hub, a new effort to provide AISFB projects, mentorship, and funding

Vael Gates28 Jul 2022 21:29 UTC

126 points

6 comments6 min readEA link

Spreading messages to help with the most important century

Holden Karnofsky25 Jan 2023 20:35 UTC

122 points

20 comments18 min readEA link

(www.cold-takes.com)

Announcing the Harvard AI Safety Team

Xander Davies30 Jun 2022 18:34 UTC

128 points

4 comments5 min readEA link

AGI Safety Fundamentals programme is contracting a low-code engineer

Jamie Bernardi26 Aug 2022 15:43 UTC

39 points

4 comments5 min readEA link

Retrospective on the AI Safety Field Building Hub

Vael Gates2 Feb 2023 2:06 UTC

56 points

2 comments9 min readEA link

Concrete Steps to Get Started in Transformer Mechanistic Interpretability

Neel Nanda26 Dec 2022 13:00 UTC

18 points

0 comments12 min readEA link

Resources that (I think) new alignment researchers should know about

Akash28 Oct 2022 22:13 UTC

20 points

2 comments1 min readEA link

Are alignment researchers devoting enough time to improving their research capacity?

Carson Jones4 Nov 2022 0:58 UTC

11 points

1 comment1 min readEA link

The Tree of Life: Stanford AI Alignment Theory of Change

Gabriel Mukobi2 Jul 2022 18:32 UTC

68 points

5 comments14 min readEA link

What are some low-cost outside-the-box ways to do/fund alignment research?

trevor111 Nov 2022 5:57 UTC

2 points

3 comments1 min readEA link

Podcast: Shoshannah Tekofsky on skilling up in AI safety, visiting Berkeley, and developing novel research ideas

Akash25 Nov 2022 20:47 UTC

14 points

0 comments1 min readEA link

Update on Harvard AI Safety Team and MIT AI Alignment

Xander Davies2 Dec 2022 6:09 UTC

69 points

3 comments1 min readEA link

The Benefits of Distillation in Research

Jonas Hallgren4 Mar 2023 19:19 UTC

43 points

2 comments5 min readEA link

[Question] I have thousands of copies of HPMOR in Russian. How to use them with the most impact?

Samin27 Dec 2022 11:07 UTC

35 points

10 comments1 min readEA link

AI safety university groups: a promising opportunity to reduce existential risk

mic30 Jun 2022 18:37 UTC

50 points

1 comment11 min readEA link

Results for a survey of tool use and workflows in alignment research

jacquesthibs19 Dec 2022 15:19 UTC

29 points

0 comments1 min readEA link

Transcripts of interviews with AI researchers

Vael Gates9 May 2022 6:03 UTC

140 points

14 comments2 min readEA link

Announcing aisafety.training

JJ Hepburn17 Jan 2023 1:55 UTC

108 points

4 comments1 min readEA link

How many people are working (directly) on reducing existential risk from AI?

Benjamin Hilton17 Jan 2023 14:03 UTC

117 points

3 comments4 min readEA link

(80000hours.org)

Establishing Oxford’s AI Safety Student Group: Lessons Learnt and Our Model

Wilkin123421 Sep 2022 7:57 UTC

71 points

3 comments1 min readEA link

AI Safety Seems Hard to Measure

Holden Karnofsky11 Dec 2022 1:31 UTC

88 points

2 comments14 min readEA link

Recursive Middle Manager Hell

Raemon17 Jan 2023 19:02 UTC

78 points

2 comments1 min readEA link

AGI safety field building projects I’d like to see

Severin24 Jan 2023 23:30 UTC

25 points

2 comments1 min readEA link

We Ran an Alignment Workshop

aiden ament21 Jan 2023 5:37 UTC

6 points

0 comments3 min readEA link

Vael Gates: Risks from Advanced AI (June 2022)

Vael Gates14 Jun 2022 0:49 UTC

45 points

5 comments30 min readEA link

Why I think that teaching philosophy is high impact

Eleni_A19 Dec 2022 23:00 UTC

17 points

2 comments2 min readEA link

Air-gapping evaluation and support

Ryan Kidd26 Dec 2022 22:52 UTC

18 points

12 comments1 min readEA link

AI Safety field-building projects I’d like to see

Akash11 Sep 2022 23:45 UTC

19 points

4 comments7 min readEA link

(www.lesswrong.com)

New Canada AI Safety & Governance community

Wyatt Tessari L'Allié29 Aug 2022 15:58 UTC

31 points

2 comments1 min readEA link

Stress Externalities More in AI Safety Pitches

NickGabs26 Sep 2022 20:31 UTC

31 points

13 comments2 min readEA link

[Question] Best introductory overviews of AGI safety?

Jakub Kraus13 Dec 2022 19:04 UTC

13 points

8 comments2 min readEA link

(www.lesswrong.com)

We all teach: here’s how to do it better

Michael Noetel30 Sep 2022 2:06 UTC

158 points

12 comments24 min readEA link

[Question] Does China have AI alignment resources/institutions? How can we prioritize creating more?

Jakub Kraus4 Aug 2022 19:23 UTC

17 points

9 comments1 min readEA link

Analysis of AI Safety surveys for field-building insights

Ash Jafari5 Dec 2022 17:37 UTC

24 points

7 comments5 min readEA link

What AI Safety Materials Do ML Researchers Find Compelling?

Vael Gates28 Dec 2022 2:03 UTC

129 points

12 comments1 min readEA link

Announcing an Empirical AI Safety Program

Joshc13 Sep 2022 21:39 UTC

64 points

7 comments2 min readEA link

AI Safety Microgrant Round

Chris Leong14 Nov 2022 4:25 UTC

81 points

1 comment3 min readEA link

Resources I send to AI researchers about AI safety

Vael Gates11 Jan 2023 1:24 UTC

32 points

0 comments1 min readEA link

Why people want to work on AI safety (but don’t)

Emily Grundy24 Jan 2023 6:41 UTC

67 points

10 comments7 min readEA link

AI Safety Unconference NeurIPS 2022

Orpheus_Lummis7 Nov 2022 15:39 UTC

13 points

5 comments1 min readEA link

(aisafetyevents.org)

AI Safety Arguments: An Interactive Guide

Lukas Trötzmüller1 Feb 2023 19:21 UTC

32 points

5 comments3 min readEA link

“AI Risk Discussions” website: Exploring interviews from 97 AI Researchers

Vael Gates2 Feb 2023 1:00 UTC

41 points

1 comment1 min readEA link

Predicting researcher interest in AI alignment

Vael Gates2 Feb 2023 0:58 UTC

30 points

0 comments21 min readEA link

(docs.google.com)

Interviews with 97 AI Researchers: Quantitative Analysis

Maheen Shermohammed2 Feb 2023 4:50 UTC

73 points

4 comments7 min readEA link

A Brief Overview of AI Safety/Alignment Orgs, Fields, Researchers, and Resources for ML Researchers

Austin Witte2 Feb 2023 6:19 UTC

18 points

5 comments2 min readEA link

Talk to me about your summer/career plans

Akash31 Jan 2023 18:29 UTC

30 points

0 comments1 min readEA link

Problems of people new to AI safety and my project ideas to mitigate them

Igor Ivanov3 Mar 2023 17:35 UTC

14 points

0 comments7 min readEA link

A Proposed Approach for AI Safety Movement Building: Projects, Professions, Skills, and Ideas for the Future [long post][bounty for feedback]

PeterSlattery22 Mar 2023 0:54 UTC

20 points

8 comments32 min readEA link

No comments.

Build­ing the field of AI safety

Related entries

Building the field of AI safety