RSS

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.

Related entries

AI risk | AI safety | existential risk | building effective altruism

Tran­scripts of in­ter­views with AI researchers

Vael Gates9 May 2022 6:03 UTC
140 points
14 comments2 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

An­nounc­ing the Har­vard AI Safety Team

Xander12330 Jun 2022 18:34 UTC
128 points
4 comments5 min readEA link

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

mic30 Jun 2022 18:37 UTC
52 points
1 comment11 min readEA link

The Tree of Life: Stan­ford AI Align­ment The­ory of Change

Gabriel Mukobi2 Jul 2022 18:32 UTC
69 points
5 comments14 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

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

JakubK4 Aug 2022 19:23 UTC
18 points
9 comments1 min readEA link

AGI Safety Fun­da­men­tals pro­gramme is con­tract­ing a low-code engineer

Jamie B26 Aug 2022 15:43 UTC
39 points
4 comments5 min readEA link

*New* Canada AI Safety & Gover­nance community

Wyatt Tessari L'Allié29 Aug 2022 15:58 UTC
31 points
2 comments1 min readEA link

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

Akash11 Sep 2022 23:45 UTC
30 points
4 comments7 min readEA link
(www.lesswrong.com)

An­nounc­ing an Em­piri­cal AI Safety Program

Joshc13 Sep 2022 21:39 UTC
64 points
7 comments2 min readEA link

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

Wilkin123421 Sep 2022 7:57 UTC
72 points
3 comments1 min readEA link

Stress Ex­ter­nal­ities More in AI Safety Pitches

NickGabs26 Sep 2022 20:31 UTC
31 points
9 comments2 min readEA link

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

Michael Noetel30 Sep 2022 2:06 UTC
168 points
12 comments24 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

AI Safety Un­con­fer­ence NeurIPS 2022

Orpheus_Lummis7 Nov 2022 15:39 UTC
13 points
5 comments1 min readEA link
(aisafetyevents.org)

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

AI Safety Micro­grant Round

Chris Leong14 Nov 2022 4:25 UTC
81 points
3 comments3 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

An­nounc­ing the Cam­bridge Bos­ton Align­ment Ini­ti­a­tive [Hiring!]

kuhanj2 Dec 2022 1:07 UTC
83 points
0 comments1 min readEA link

Up­date on Har­vard AI Safety Team and MIT AI Alignment

Xander1232 Dec 2022 6:09 UTC
70 points
3 comments1 min readEA link

Anal­y­sis of AI Safety sur­veys for field-build­ing insights

Ash Jafari5 Dec 2022 17:37 UTC
30 points
7 comments5 min readEA link

AI Safety Seems Hard to Measure

Holden Karnofsky11 Dec 2022 1:31 UTC
90 points
3 comments14 min readEA link
(www.cold-takes.com)

[Question] Best in­tro­duc­tory overviews of AGI safety?

JakubK13 Dec 2022 19:04 UTC
21 points
8 comments2 min readEA link
(www.lesswrong.com)

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

jacquesthibs19 Dec 2022 15:19 UTC
30 points
0 comments1 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

Con­crete Steps to Get Started in Trans­former Mechanis­tic Interpretability

Neel Nanda26 Dec 2022 13:00 UTC
18 points
0 comments12 min readEA link

Air-gap­ping eval­u­a­tion and support

Ryan Kidd26 Dec 2022 22:52 UTC
22 points
12 comments1 min readEA link

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

MikhailSamin27 Dec 2022 11:07 UTC
39 points
10 comments1 min readEA link

What AI Safety Ma­te­ri­als Do ML Re­searchers Find Com­pel­ling?

Vael Gates28 Dec 2022 2:03 UTC
130 points
12 comments1 min readEA link

Re­sources I send to AI re­searchers about AI safety

Vael Gates11 Jan 2023 1:24 UTC
42 points
0 comments1 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
116 points
3 comments4 min readEA link
(80000hours.org)

Re­cur­sive Mid­dle Man­ager Hell

Raemon17 Jan 2023 19:02 UTC
73 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

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

pradyuprasad23 Jan 2023 4:09 UTC
56 points
5 comments2 min readEA link

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

Emily Grundy24 Jan 2023 6:41 UTC
70 points
10 comments7 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

Spread­ing mes­sages to help with the most im­por­tant century

Holden Karnofsky25 Jan 2023 20:35 UTC
123 points
21 comments18 min readEA link
(www.cold-takes.com)

Talk to me about your sum­mer/​ca­reer plans

Akash31 Jan 2023 18:29 UTC
31 points
0 comments1 min readEA link

AI Safety Ar­gu­ments: An In­ter­ac­tive Guide

Lukas Trötzmüller1 Feb 2023 19:21 UTC
32 points
5 comments3 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)

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

Vael Gates2 Feb 2023 1:00 UTC
46 points
1 comment1 min readEA link

Ret­ro­spec­tive on the AI Safety Field Build­ing Hub

Vael Gates2 Feb 2023 2:06 UTC
64 points
2 comments9 min readEA link

In­ter­views with 97 AI Re­searchers: Quan­ti­ta­tive Analysis

Maheen Shermohammed2 Feb 2023 4:50 UTC
76 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

Jobs that can help with the most im­por­tant century

Holden Karnofsky12 Feb 2023 18:19 UTC
52 points
2 comments32 min readEA link
(www.cold-takes.com)

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

Igor Ivanov3 Mar 2023 17:35 UTC
19 points
0 comments7 min readEA link

The Benefits of Distil­la­tion in Research

Jonas Hallgren4 Mar 2023 19:19 UTC
45 points
2 comments5 min readEA link

Part 3: 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
21 points
8 comments32 min readEA link

No­body’s on the ball on AGI alignment

leopold29 Mar 2023 14:26 UTC
324 points
63 comments9 min readEA link
(www.forourposterity.com)

Re­cruit the World’s best for AGI Alignment

Greg_Colbourn30 Mar 2023 16:41 UTC
34 points
8 comments22 min readEA link

Vael Gates: Risks from Highly-Ca­pable AI (March 2023)

Vael Gates1 Apr 2023 20:54 UTC
31 points
4 comments1 min readEA link
(docs.google.com)

[Question] Plat­form for Pro­ject Spit­bal­ling? (e.g., for AI field build­ing)

Harrison Durland3 Apr 2023 15:45 UTC
7 points
2 comments1 min readEA link

Keep Chas­ing AI Safety Press Coverage

RedStateBlueState4 Apr 2023 20:40 UTC
106 points
16 comments5 min readEA link

AISafety.world is a map of the AIS ecosystem

Hamish McDoodles6 Apr 2023 11:47 UTC
189 points
8 comments1 min readEA link

Stampy’s AI Safety Info—New Distil­la­tions #1 [March 2023]

markov7 Apr 2023 11:35 UTC
18 points
0 comments2 min readEA link
(aisafety.info)

All AGI Safety ques­tions wel­come (es­pe­cially ba­sic ones) [April 2023]

StevenKaas8 Apr 2023 4:21 UTC
111 points
174 comments1 min readEA link

SERI MATS—Sum­mer 2023 Cohort

a_e_r8 Apr 2023 15:32 UTC
36 points
2 comments1 min readEA link

[SEE NEW EDITS] No, *You* Need to Write Clearer

NicholasKross29 Apr 2023 5:04 UTC
71 points
8 comments1 min readEA link
(www.thinkingmuchbetter.com)

How MATS ad­dresses “mass move­ment build­ing” concerns

Ryan Kidd4 May 2023 0:55 UTC
76 points
4 comments1 min readEA link

Chilean AIS Hackathon Retrospective

Agustín Covarrubias9 May 2023 1:34 UTC
67 points
0 comments5 min readEA link

An­nounc­ing “Key Phenom­ena in AI Risk” (fa­cil­i­tated read­ing group)

nora9 May 2023 16:52 UTC
27 points
0 comments2 min readEA link

Thread: Reflec­tions on the AGI Safety Fun­da­men­tals course?

Clifford18 May 2023 13:11 UTC
27 points
7 comments1 min readEA link

[Question] AI strat­egy ca­reer pipeline

Zach Stein-Perlman22 May 2023 0:00 UTC
72 points
23 comments1 min readEA link

Ad­vice for En­ter­ing AI Safety Research

stecas2 Jun 2023 20:46 UTC
14 points
1 comment1 min readEA link

An­nounc­ing AISafety.info’s Write-a-thon (June 16-18) and Se­cond Distil­la­tion Fel­low­ship (July 3-Oc­to­ber 2)

StevenKaas3 Jun 2023 2:03 UTC
12 points
1 comment1 min readEA link

De­com­pos­ing al­ign­ment to take ad­van­tage of paradigms

Christopher King4 Jun 2023 14:26 UTC
2 points
0 comments4 min readEA link

AI Safety Fun­da­men­tals: An In­for­mal Co­hort Start­ing Soon! (cross-posted to less­wrong.com)

Tiago4 Jun 2023 18:21 UTC
6 points
0 comments1 min readEA link
(www.lesswrong.com)

AISafety.info “How can I help?” FAQ

StevenKaas5 Jun 2023 22:09 UTC
48 points
1 comment1 min readEA link

Why EA Com­mu­nity building

Rob Gledhill14 Jun 2023 20:48 UTC
73 points
7 comments5 min readEA link

Thoughts about AI safety field-build­ing in LMIC

Renan Araujo23 Jun 2023 23:22 UTC
56 points
4 comments12 min readEA link

Let’s set new AI safety ac­tors up for success

michel26 Jun 2023 21:17 UTC
33 points
1 comment9 min readEA link

AI Safety Field Build­ing vs. EA CB

kuhanj26 Jun 2023 23:21 UTC
78 points
16 comments6 min readEA link

Where on the con­tinuum of pure EA to pure AIS should you be? (Uni Group Or­ga­niz­ers Fo­cus)

jessica_mccurdy26 Jun 2023 23:46 UTC
43 points
0 comments5 min readEA link

Wash­ing­ton Post ar­ti­cle about EA uni­ver­sity groups

Lizka5 Jul 2023 12:58 UTC
39 points
5 comments1 min readEA link

Model­ing the im­pact of AI safety field-build­ing programs

Center for AI Safety10 Jul 2023 17:22 UTC
79 points
0 comments7 min readEA link

Cost-effec­tive­ness of stu­dent pro­grams for AI safety research

Center for AI Safety10 Jul 2023 17:23 UTC
51 points
6 comments15 min readEA link

Cost-effec­tive­ness of pro­fes­sional field-build­ing pro­grams for AI safety research

Center for AI Safety10 Jul 2023 17:26 UTC
35 points
2 comments18 min readEA link

An Overview of the AI Safety Fund­ing Situation

Stephen McAleese12 Jul 2023 14:54 UTC
127 points
12 comments15 min readEA link

Align­ment Me­gapro­jects: You’re Not Even Try­ing to Have Ideas

NicholasKross12 Jul 2023 23:39 UTC
7 points
1 comment1 min readEA link

Cam­bridge AI Safety Hub is look­ing for full- or part-time organisers

hannah15 Jul 2023 14:31 UTC
12 points
0 comments1 min readEA link

Align­ment Grant­mak­ing is Fund­ing-Limited Right Now [cross­post]

johnswentworth2 Aug 2023 20:37 UTC
82 points
13 comments1 min readEA link
(www.lesswrong.com)

Join AISafety.info’s Writ­ing & Edit­ing Hackathon (Aug 25-28) (Prizes to be won!)

Siao Si5 Aug 2023 14:06 UTC
15 points
0 comments1 min readEA link

Up­date on cause area fo­cus work­ing group

Bastian_Stern10 Aug 2023 1:21 UTC
140 points
18 comments5 min readEA link

Su­per­vised Pro­gram for Align­ment Re­search (SPAR) at UC Berkeley: Spring 2023 summary

mic19 Aug 2023 2:32 UTC
18 points
0 comments6 min readEA link
(www.lesswrong.com)

Ideas for im­prov­ing epistemics in AI safety outreach

mic21 Aug 2023 19:56 UTC
31 points
0 comments3 min readEA link
(www.lesswrong.com)

Re­think Pri­ori­ties is look­ing for a (Co-)Founder for a New Pro­ject: Field Build­ing in Univer­si­ties for AI Policy Ca­reers in the US

KevinN28 Aug 2023 16:01 UTC
59 points
0 comments6 min readEA link
(careers.rethinkpriorities.org)

Ap­ply to lead a pro­ject dur­ing the next vir­tual AI Safety Camp

Linda Linsefors13 Sep 2023 13:29 UTC
16 points
0 comments1 min readEA link
(aisafety.camp)

Re­la­tion­ship be­tween EA Com­mu­nity and AI safety

Tom Barnes18 Sep 2023 13:49 UTC
156 points
15 comments1 min readEA link

I de­signed an AI safety course (for a philos­o­phy de­part­ment)

Eleni_A23 Sep 2023 21:56 UTC
27 points
3 comments2 min readEA link

ARENA 2.0 - Im­pact Report

TheMcDouglas26 Sep 2023 17:13 UTC
17 points
0 comments13 min readEA link

Pro­jects I would like to see (pos­si­bly at AI Safety Camp)

Linda Linsefors27 Sep 2023 21:27 UTC
9 points
0 comments1 min readEA link

Ob­ser­va­tions on the fund­ing land­scape of EA and AI safety

Vilhelm Skoglund2 Oct 2023 9:45 UTC
135 points
11 comments15 min readEA link

Ap­ply for MATS Win­ter 2023-24!

Rocket21 Oct 2023 2:34 UTC
34 points
2 comments5 min readEA link
(www.lesswrong.com)

What we learned from run­ning an Aus­tralian AI Safety Unconference

Alexander Saeri26 Oct 2023 0:46 UTC
34 points
0 comments5 min readEA link

AI safety field-build­ing sur­vey: Ta­lent needs, in­fras­truc­ture needs, and re­la­tion­ship to EA

michel27 Oct 2023 21:08 UTC
67 points
3 comments9 min readEA link

On run­ning a city-wide uni­ver­sity group

gergo6 Nov 2023 9:43 UTC
26 points
3 comments9 min readEA link

20+ tips, tricks, les­sons and thoughts on host­ing hackathons

gergo6 Nov 2023 10:59 UTC
14 points
0 comments11 min readEA link

An­nounc­ing Athena—Women in AI Align­ment Research

Claire Short7 Nov 2023 22:02 UTC
179 points
28 comments3 min readEA link

Sur­vey on the ac­cel­er­a­tion risks of our new RFPs to study LLM capabilities

Ajeya10 Nov 2023 23:59 UTC
38 points
1 comment8 min readEA link

Dutch AI Safety Co­or­di­na­tion Fo­rum: An Experiment

HenningB21 Nov 2023 16:18 UTC
21 points
0 comments4 min readEA link

Shal­low re­view of live agen­das in al­ign­ment & safety

Gavin27 Nov 2023 11:33 UTC
76 points
8 comments29 min readEA link

On­board­ing stu­dents to EA/​AIS in 4 days with an in­ten­sive fellowship

gergo5 Dec 2023 10:07 UTC
15 points
0 comments4 min readEA link

You can run more than one fel­low­ship per semester if you want to

gergo12 Dec 2023 8:49 UTC
6 points
1 comment2 min readEA link

ML4Good UK—Ap­pli­ca­tions Open

Nia2 Jan 2024 18:20 UTC
21 points
0 comments1 min readEA link

The Hasty Start of Bu­dapest AI Safety, 6-month up­date from a non-STEM founder

gergo3 Jan 2024 12:56 UTC
9 points
1 comment7 min readEA link

Learn­ing Math in Time for Alignment

NicholasKross9 Jan 2024 1:02 UTC
10 points
0 comments1 min readEA link

Good job op­por­tu­ni­ties for helping with the most im­por­tant century

Holden Karnofsky18 Jan 2024 19:21 UTC
49 points
1 comment4 min readEA link
(www.cold-takes.com)

Im­pact Assess­ment of AI Safety Camp (Arb Re­search)

Sam Holton23 Jan 2024 16:32 UTC
84 points
23 comments11 min readEA link

Cost-effec­tive­ness anal­y­sis of ~1260 USD worth of so­cial me­dia ads for fel­low­ship marketing

gergo25 Jan 2024 15:18 UTC
54 points
4 comments2 min readEA link

[Question] Work­shop (hackathon, res­i­dence pro­gram, etc.) about for-profit AI Safety pro­jects?

Roman Leventov26 Jan 2024 9:49 UTC
13 points
1 comment1 min readEA link

AI safety needs to scale, and here’s how you can do it

Esben Kran2 Feb 2024 7:17 UTC
31 points
2 comments5 min readEA link
(apartresearch.com)

My Proven AI Safety Ex­pla­na­tion (as a com­put­ing stu­dent)

Mica White6 Feb 2024 3:58 UTC
8 points
4 comments6 min readEA link

Offer­ing AI safety sup­port calls for ML professionals

Vael Gates15 Feb 2024 23:48 UTC
51 points
1 comment1 min readEA link

An­nounc­ing AI Safety Bulgaria

Aleksandar N. Angelov3 Mar 2024 17:53 UTC
10 points
0 comments1 min readEA link

We are shar­ing a new web­site tem­plate for AI Safety groups!

AIS Hungary13 Mar 2024 16:40 UTC
8 points
2 comments1 min readEA link
No comments.