Newsletters

Tag

QAPR 4: Inductive biases

Quintin PopeOct 10, 2022, 10:08 PM

67 points

2 comments18 min readLW link

Forecasting Newsletter. June 2020.

NunoSempereJul 1, 2020, 9:46 AM

27 points

0 comments8 min readLW link

[MLSN #8] Mechanistic interpretability, using law to inform AI alignment, scaling laws for proxy gaming

Dan H and TW123

Feb 20, 2023, 3:54 PM

20 points

0 comments4 min readLW link

(newsletter.mlsafety.org)

Quintin’s alignment papers roundup—week 1

Quintin PopeSep 10, 2022, 6:39 AM

120 points

6 comments9 min readLW link

[AN #115]: AI safety research problems in the AI-GA framework

Rohin ShahSep 2, 2020, 5:10 PM

19 points

16 comments6 min readLW link

(mailchi.mp)

[AN #102]: Meta learning by GPT-3, and a list of full proposals for AI alignment

Rohin ShahJun 3, 2020, 5:20 PM

38 points

6 comments10 min readLW link

(mailchi.mp)

Hiatus: EA and LW post summaries

Zoe WilliamsMay 17, 2023, 5:17 PM

14 points

0 comments1 min readLW link

Progress links and tweets, 2023-05-16

jasoncrawfordMay 16, 2023, 8:54 PM

14 points

0 comments1 min readLW link

(rootsofprogress.org)

The Paris AI Anti-Safety Summit

ZviFeb 12, 2025, 2:00 PM

129 points

21 comments21 min readLW link

(thezvi.wordpress.com)

EA & LW Forum Weekly Summary (20th − 26th March 2023)

Zoe WilliamsMar 27, 2023, 8:46 PM

4 points

0 comments1 min readLW link

AI #58: Stargate AGI

ZviApr 4, 2024, 1:10 PM

49 points

9 comments60 min readLW link

(thezvi.wordpress.com)

AI Safety Newsletter #7: Disinformation, Governance Recommendations for AI labs, and Senate Hearings on AI

Dan HMay 23, 2023, 9:47 PM

25 points

0 comments6 min readLW link

(newsletter.safe.ai)

AI #53: One More Leap

ZviFeb 29, 2024, 4:10 PM

45 points

0 comments38 min readLW link

(thezvi.wordpress.com)

[AN #112]: Engineering a Safer World

Rohin ShahAug 13, 2020, 5:20 PM

26 points

2 comments12 min readLW link

(mailchi.mp)

AI #6: Agents of Change

ZviApr 6, 2023, 2:00 PM

79 points

13 comments47 min readLW link

(thezvi.wordpress.com)

AI Safety Newsletter #1 [CAIS Linkpost]

Akash, Dan H and ozhang

Apr 10, 2023, 8:18 PM

45 points

0 comments4 min readLW link

(newsletter.safe.ai)

[MLSN #9] Verifying large training runs, security risks from LLM access to APIs, why natural selection may favor AIs over humans

Dan H and TW123

Apr 11, 2023, 4:03 PM

11 points

0 comments6 min readLW link

(newsletter.mlsafety.org)

AI #7: Free Agency

ZviApr 13, 2023, 4:20 PM

33 points

12 comments47 min readLW link

(thezvi.wordpress.com)

Navigating AI Risks (NAIR) #1: Slowing Down AI

simeon_cApr 14, 2023, 2:35 PM

11 points

3 comments1 min readLW link

(navigatingairisks.substack.com)

AI Impacts Quarterly Newsletter, Jan-Mar 2023

HarlanApr 17, 2023, 10:10 PM

5 points

0 comments3 min readLW link

(blog.aiimpacts.org)

AI #13: Potential Algorithmic Improvements

ZviMay 25, 2023, 3:40 PM

45 points

4 comments67 min readLW link

(thezvi.wordpress.com)

AI Safety Newsletter #8: Rogue AIs, how to screen for AI risks, and grants for research on democratic governance of AI

Dan HMay 30, 2023, 11:52 AM

20 points

0 comments6 min readLW link

(newsletter.safe.ai)

AI #14: A Very Good Sentence

ZviJun 1, 2023, 9:30 PM

118 points

30 comments65 min readLW link

(thezvi.wordpress.com)

AI #59: Model Updates

ZviApr 11, 2024, 2:20 PM

30 points

2 comments63 min readLW link

(thezvi.wordpress.com)

AISN #9: Statement on Extinction Risks, Competitive Pressures, and When Will AI Reach Human-Level?

Dan HJun 6, 2023, 4:10 PM

12 points

0 comments7 min readLW link

(newsletter.safe.ai)

AI #15: The Principle of Charity

ZviJun 8, 2023, 12:10 PM

73 points

16 comments44 min readLW link

(thezvi.wordpress.com)

AI #16: AI in the UK

ZviJun 15, 2023, 1:20 PM

46 points

20 comments54 min readLW link

(thezvi.wordpress.com)

Summaries of top forum posts (17th − 23rd April 2023)

Zoe WilliamsApr 24, 2023, 4:13 AM

18 points

0 comments1 min readLW link

AI #17: The Litany

ZviJun 22, 2023, 2:30 PM

95 points

34 comments56 min readLW link

(thezvi.wordpress.com)

AI Safety Newsletter #3: AI policy proposals and a new challenger approaches

ozhangApr 25, 2023, 4:15 PM

33 points

0 comments1 min readLW link

AI #18: The Great Debate Debate

ZviJun 29, 2023, 4:20 PM

47 points

9 comments52 min readLW link

(thezvi.wordpress.com)

AI Alignment [Incremental Progress Units] this Week (10/22/23)

Logan ZoellnerOct 23, 2023, 8:32 PM

22 points

0 comments6 min readLW link

(midwitalignment.substack.com)

AISN #12: Policy Proposals from NTIA’s Request for Comment and Reconsidering Instrumental Convergence

Dan HJun 27, 2023, 5:20 PM

6 points

0 comments1 min readLW link

AI #19: Hofstadter, Sutskever, Leike

ZviJul 6, 2023, 12:50 PM

60 points

16 comments40 min readLW link

(thezvi.wordpress.com)

Monthly Roundup #8: July 2023

ZviJul 3, 2023, 1:20 PM

40 points

4 comments46 min readLW link

(thezvi.wordpress.com)

AISN #13: An interdisciplinary perspective on AI proxy failures, new competitors to ChatGPT, and prompting language models to misbehave

Dan HJul 5, 2023, 3:33 PM

13 points

0 comments1 min readLW link

AISN #25: White House Executive Order on AI, UK AI Safety Summit, and Progress on Voluntary Evaluations of AI Risks

Dan HOct 31, 2023, 7:34 PM

35 points

1 comment6 min readLW link

(newsletter.safe.ai)

AI #9: The Merge and the Million Tokens

ZviApr 27, 2023, 2:20 PM

36 points

8 comments53 min readLW link

(thezvi.wordpress.com)

Medical Roundup #3

ZviJul 9, 2024, 1:10 PM

39 points

4 comments19 min readLW link

(thezvi.wordpress.com)

AISN #26: National Institutions for AI Safety, Results From the UK Summit, and New Releases From OpenAI and xAI

Corin Katzke, allison huang and Dan H

Nov 15, 2023, 4:07 PM

13 points

0 comments6 min readLW link

(newsletter.safe.ai)

AI #72: Denying the Future

ZviJul 11, 2024, 3:00 PM

45 points

8 comments41 min readLW link

(thezvi.wordpress.com)

AI #103: Show Me the Money

ZviFeb 13, 2025, 3:20 PM

30 points

9 comments58 min readLW link

(thezvi.wordpress.com)

AISN #33: Reassessing AI and Biorisk Plus, Consolidation in the Corporate AI Landscape, and National Investments in AI

Corin Katzke, Alexa Pan and Dan H

Apr 12, 2024, 4:10 PM

13 points

0 comments9 min readLW link

(newsletter.safe.ai)

Llama Llama-3-405B?

ZviJul 24, 2024, 7:40 PM

51 points

9 comments30 min readLW link

(thezvi.wordpress.com)

AI #41: Bring in the Other Gemini

ZviDec 7, 2023, 3:10 PM

46 points

16 comments52 min readLW link

(thezvi.wordpress.com)

AISN #27: Defensive Accelerationism, A Retrospective On The OpenAI Board Saga, And A New AI Bill From Senators Thune And Klobuchar

Dan H, Corin Katzke and allison huang

Dec 7, 2023, 3:59 PM

13 points

0 comments6 min readLW link

(newsletter.safe.ai)

AI #74: GPT-4o Mini Me and Llama 3

ZviJul 25, 2024, 1:50 PM

30 points

6 comments36 min readLW link

(thezvi.wordpress.com)

AISN#14: OpenAI’s ‘Superalignment’ team, Musk’s xAI launches, and developments in military AI use

Dan HJul 12, 2023, 4:58 PM

16 points

0 comments1 min readLW link

Alignment Newsletter #36

Rohin ShahDec 12, 2018, 1:10 AM

21 points

0 comments11 min readLW link

(mailchi.mp)

Alignment Newsletter #47

Rohin ShahMar 4, 2019, 4:30 AM

18 points

0 comments8 min readLW link

(mailchi.mp)

AI #20: Code Interpreter and Claude 2.0 for Everyone

ZviJul 13, 2023, 2:00 PM

60 points

9 comments56 min readLW link

(thezvi.wordpress.com)

AISN #29: Progress on the EU AI Act Plus, the NY Times sues OpenAI for Copyright Infringement, and Congressional Questions about Research Standards in AI Safety

Dan H and Corin Katzke

Jan 4, 2024, 4:09 PM

8 points

0 comments6 min readLW link

(newsletter.safe.ai)

AISN#15: China and the US take action to regulate AI, results from a tournament forecasting AI risk, updates on xAI’s plan, and Meta releases its open-source and commercially available Llama 2

Corin Katzke and Dan H

Jul 19, 2023, 1:01 PM

16 points

0 comments6 min readLW link

(newsletter.safe.ai)

AISN #28: Center for AI Safety 2023 Year in Review

Dan HDec 23, 2023, 9:31 PM

30 points

1 comment5 min readLW link

(newsletter.safe.ai)

AI #95: o1 Joins the API

ZviDec 19, 2024, 3:10 PM

58 points

1 comment41 min readLW link

(thezvi.wordpress.com)

[AN #118]: Risks, solutions, and prioritization in a world with many AI systems

Rohin ShahSep 23, 2020, 6:20 PM

15 points

6 comments10 min readLW link

(mailchi.mp)

Progress links and tweets, 2023-07-20: “A goddess enthroned on a car”

jasoncrawfordJul 20, 2023, 6:28 PM

12 points

4 comments2 min readLW link

(rootsofprogress.org)

AI #22: Into the Weeds

ZviJul 27, 2023, 5:40 PM

49 points

8 comments84 min readLW link

(thezvi.wordpress.com)

AISN #16: White House Secures Voluntary Commitments from Leading AI Labs and Lessons from Oppenheimer

Corin Katzke and Dan H

Jul 25, 2023, 4:58 PM

6 points

0 comments6 min readLW link

(newsletter.safe.ai)

AISN #17: Automatically Circumventing LLM Guardrails, the Frontier Model Forum, and Senate Hearing on AI Oversight

Dan HAug 1, 2023, 3:40 PM

8 points

0 comments8 min readLW link

(newsletter.safe.ai)

AISN #16: White House Secures Voluntary Commitments from Leading AI Labs and Lessons from Oppenheimer

Dan H and Corin Katzke

Aug 1, 2023, 3:39 PM

3 points

0 comments6 min readLW link

(newsletter.safe.ai)

AI #23: Fundamental Problems with RLHF

ZviAug 3, 2023, 12:50 PM

59 points

9 comments41 min readLW link

(thezvi.wordpress.com)

AI #24: Week of the Podcast

ZviAug 10, 2023, 3:00 PM

49 points

5 comments44 min readLW link

(thezvi.wordpress.com)

AISN #18: Challenges of Reinforcement Learning from Human Feedback, Microsoft’s Security Breach, and Conceptual Research on AI Safety

Dan HAug 8, 2023, 3:52 PM

13 points

0 comments1 min readLW link

(newsletter.safe.ai)

AI #75: Math is Easier

ZviAug 1, 2024, 1:40 PM

46 points

25 comments72 min readLW link

(thezvi.wordpress.com)

Progress links digest, 2023-08-09: US adds new nuclear, Katalin Karikó interview, and more

jasoncrawfordAug 9, 2023, 7:22 PM

18 points

0 comments3 min readLW link

(rootsofprogress.org)

AI #76: Six Shorts Stories About OpenAI

ZviAug 8, 2024, 1:50 PM

53 points

10 comments48 min readLW link

(thezvi.wordpress.com)

Startup Roundup #2

ZviAug 6, 2024, 1:30 PM

45 points

0 comments32 min readLW link

(thezvi.wordpress.com)

AI #83: The Mask Comes Off

ZviSep 26, 2024, 12:00 PM

82 points

20 comments36 min readLW link

(thezvi.wordpress.com)

Monthly Roundup #25: December 2024

ZviDec 23, 2024, 2:20 PM

18 points

3 comments26 min readLW link

(thezvi.wordpress.com)

AISN #34: New Military AI Systems Plus, AI Labs Fail to Uphold Voluntary Commitments to UK AI Safety Institute, and New AI Policy Proposals in the US Senate

Corin Katzke and Dan H

May 2, 2024, 4:12 PM

6 points

0 comments8 min readLW link

(newsletter.safe.ai)

AISN #32: Measuring and Reducing Hazardous Knowledge in LLMs Plus, Forecasting the Future with LLMs, and Regulatory Markets

Corin Katzke and Dan H

Mar 7, 2024, 4:39 PM

8 points

0 comments8 min readLW link

(newsletter.safe.ai)

AI #86: Just Think of the Potential

ZviOct 17, 2024, 3:10 PM

58 points

8 comments57 min readLW link

(thezvi.wordpress.com)

Housing Roundup #10

ZviOct 29, 2024, 1:50 PM

32 points

2 comments32 min readLW link

(thezvi.wordpress.com)

AI #26: Fine Tuning Time

ZviAug 24, 2023, 3:30 PM

49 points

6 comments33 min readLW link

(thezvi.wordpress.com)

AI #87: Staying in Character

ZviOct 29, 2024, 7:10 AM

57 points

3 comments33 min readLW link

(thezvi.wordpress.com)

Occupational Licensing Roundup #1

ZviOct 30, 2024, 11:00 AM

65 points

11 comments11 min readLW link

(thezvi.wordpress.com)

October 2024 Progress in Guaranteed Safe AI

QuinnOct 28, 2024, 11:34 PM

7 points

0 comments1 min readLW link

(gsai.substack.com)

AI Safety at the Frontier: Paper Highlights, October ’24

gasteigerjoOct 31, 2024, 12:09 AM

3 points

0 comments9 min readLW link

(aisafetyfrontier.substack.com)

AI #88: Thanks for the Memos

ZviOct 31, 2024, 3:00 PM

46 points

5 comments77 min readLW link

(thezvi.wordpress.com)

AI #105: Hey There Alexa

ZviFeb 27, 2025, 2:30 PM

31 points

3 comments40 min readLW link

(thezvi.wordpress.com)

AI #89: Trump Card

ZviNov 7, 2024, 4:30 PM

42 points

12 comments42 min readLW link

(thezvi.wordpress.com)

AISN #35: Lobbying on AI Regulation Plus, New Models from OpenAI and Google, and Legal Regimes for Training on Copyrighted Data

Dan H and Corin Katzke

May 16, 2024, 2:29 PM

2 points

3 comments6 min readLW link

(newsletter.safe.ai)

On Dwarksh’s Podcast with Leopold Aschenbrenner

ZviJun 10, 2024, 12:40 PM

101 points

7 comments59 min readLW link

(thezvi.wordpress.com)

AISN #23: New OpenAI Models, News from Anthropic, and Representation Engineering

Dan HOct 4, 2023, 5:37 PM

15 points

2 comments5 min readLW link

(newsletter.safe.ai)

Sentinel minutes #10/2025: Trump tariffs, US/China tensions, Claude code reward hacking.

NunoSempereMar 10, 2025, 7:00 PM

25 points

0 comments10 min readLW link

(blog.sentinel-team.org)

Childhood and Education #8: Dealing with the Internet

ZviJan 6, 2025, 2:00 PM

37 points

7 comments13 min readLW link

(thezvi.wordpress.com)

[AN #129]: Explaining double descent by measuring bias and variance

Rohin ShahDec 16, 2020, 6:10 PM

14 points

1 comment7 min readLW link

(mailchi.mp)

AISN #24: Kissinger Urges US-China Cooperation on AI, China’s New AI Law, US Export Controls, International Institutions, and Open Source AI

Dan H and Corin Katzke

Oct 18, 2023, 5:06 PM

14 points

0 comments6 min readLW link

(newsletter.safe.ai)

OpenAI #10: Reflections

ZviJan 7, 2025, 5:00 PM

149 points

7 comments11 min readLW link

(thezvi.wordpress.com)

AI #98: World Ends With Six Word Story

ZviJan 9, 2025, 4:30 PM

36 points

2 comments38 min readLW link

(thezvi.wordpress.com)

[AN #145]: Our three year anniversary!

Rohin ShahApr 9, 2021, 5:48 PM

19 points

0 comments8 min readLW link

(mailchi.mp)

Forecasting Newsletter: April 2021

NunoSempereMay 1, 2021, 4:07 PM

9 points

0 comments10 min readLW link

[AN #166]: Is it crazy to claim we’re in the most important century?

Rohin ShahOct 8, 2021, 5:30 PM

52 points

5 comments8 min readLW link

(mailchi.mp)

[AN #167]: Concrete ML safety problems and their relevance to x-risk

Rohin ShahOct 20, 2021, 5:10 PM

21 points

4 comments9 min readLW link

(mailchi.mp)

[AN #170]: Analyzing the argument for risk from power-seeking AI

Rohin ShahDec 8, 2021, 6:10 PM

21 points

1 comment7 min readLW link

(mailchi.mp)

Forecasting Newsletter: January 2022

NunoSempereFeb 3, 2022, 7:22 PM

17 points

0 comments6 min readLW link

Forecasting Newsletter: February 2022

NunoSempereMar 5, 2022, 7:30 PM

36 points

0 comments9 min readLW link

On Dwarkesh Patel’s 4th Podcast With Tyler Cowen

ZviJan 10, 2025, 1:50 PM

44 points

7 comments27 min readLW link

(thezvi.wordpress.com)

[AN #173] Recent language model results from DeepMind

Rohin ShahJul 21, 2022, 2:30 AM

37 points

9 comments8 min readLW link

(mailchi.mp)

EA & LW Forums Weekly Summary (21 Aug − 27 Aug 22′)

Zoe WilliamsAug 30, 2022, 1:42 AM

57 points

4 comments12 min readLW link

AI Safety at the Frontier: Paper Highlights, December ’24

gasteigerjoJan 11, 2025, 10:54 PM

7 points

2 comments7 min readLW link

(aisafetyfrontier.substack.com)

EA & LW Forums Weekly Summary (5 − 11 Sep 22′)

Zoe WilliamsSep 12, 2022, 11:24 PM

24 points

0 comments13 min readLW link

Quintin’s alignment papers roundup—week 2

Quintin PopeSep 19, 2022, 1:41 PM

67 points

2 comments10 min readLW link

QAPR 3: interpretability-guided training of neural nets

Quintin PopeSep 28, 2022, 4:02 PM

58 points

2 comments10 min readLW link

AI #99: Farewell to Biden

ZviJan 16, 2025, 2:20 PM

54 points

5 comments58 min readLW link

(thezvi.wordpress.com)

[MLSN #6]: Transparency survey, provable robustness, ML models that predict the future

Dan HOct 12, 2022, 8:56 PM

27 points

0 comments6 min readLW link

EA & LW Forums Weekly Summary (10 − 16 Oct 22′)

Zoe WilliamsOct 17, 2022, 10:51 PM

12 points

4 comments1 min readLW link

Meta Pivots on Content Moderation

ZviJan 17, 2025, 2:20 PM

47 points

3 comments10 min readLW link

(thezvi.wordpress.com)

EA & LW Forums Weekly Summary (17 − 23 Oct 22′)

Zoe WilliamsOct 25, 2022, 2:57 AM

10 points

0 comments1 min readLW link

On DeepSeek’s r1

ZviJan 22, 2025, 7:50 PM

55 points

2 comments35 min readLW link

(thezvi.wordpress.com)

EA & LW Forums Weekly Summary (24 − 30th Oct 22′)

Zoe WilliamsNov 1, 2022, 2:58 AM

13 points

1 comment1 min readLW link

EA & LW Forums Weekly Summary (31st Oct − 6th Nov 22′)

Zoe WilliamsNov 8, 2022, 3:58 AM

12 points

1 comment1 min readLW link

EA & LW Forums Weekly Summary (7th Nov − 13th Nov 22′)

Zoe WilliamsNov 16, 2022, 3:04 AM

19 points

0 comments1 min readLW link

AI #100: Meet the New Boss

ZviJan 23, 2025, 3:40 PM

50 points

4 comments69 min readLW link

(thezvi.wordpress.com)

[Question] What AI newsletters or substacks about AI do you recommend?

wunanNov 25, 2022, 7:29 PM

6 points

1 comment1 min readLW link

EA & LW Forums Weekly Summary (14th Nov − 27th Nov 22′)

Zoe WilliamsNov 29, 2022, 11:00 PM

21 points

1 comment1 min readLW link

AISN #30: Investments in Compute and Military AI Plus, Japan and Singapore’s National AI Safety Institutes

Dan H and Corin Katzke

Jan 24, 2024, 7:38 PM

27 points

1 comment6 min readLW link

(newsletter.safe.ai)

ML Safety at NeurIPS & Paradigmatic AI Safety? MLAISU W49

Esben Kran and Steinthal

Dec 9, 2022, 10:38 AM

19 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

EA & LW Forums Weekly Summary (5th Dec − 11th Dec 22′)

Zoe WilliamsDec 13, 2022, 2:53 AM

7 points

0 comments1 min readLW link

Stargate AI-1

ZviJan 24, 2025, 3:20 PM

85 points

1 comment18 min readLW link

(thezvi.wordpress.com)

DeepSeek: Lemon, It’s Wednesday

ZviJan 29, 2025, 3:00 PM

33 points

0 comments33 min readLW link

(thezvi.wordpress.com)

Operator

ZviJan 28, 2025, 8:00 PM

35 points

1 comment11 min readLW link

(thezvi.wordpress.com)

DeepSeek Panic at the App Store

ZviJan 28, 2025, 7:30 PM

51 points

14 comments33 min readLW link

(thezvi.wordpress.com)

AI #101: The Shallow End

ZviJan 30, 2025, 2:50 PM

39 points

1 comment59 min readLW link

(thezvi.wordpress.com)

EA & LW Forum Summaries (9th Jan to 15th Jan 23′)

Zoe WilliamsJan 18, 2023, 7:29 AM

17 points

0 comments1 min readLW link

o3-mini Early Days

ZviFeb 3, 2025, 2:20 PM

45 points

0 comments15 min readLW link

(thezvi.wordpress.com)

EA & LW Forum Weekly Summary (16th − 22nd Jan ’23)

Zoe WilliamsJan 23, 2023, 3:46 AM

13 points

0 comments1 min readLW link

We’re in Deep Research

ZviFeb 4, 2025, 5:20 PM

45 points

2 comments20 min readLW link

(thezvi.wordpress.com)

EA & LW Forum Weekly Summary (23rd − 29th Jan ’23)

Zoe WilliamsJan 31, 2023, 12:36 AM

12 points

0 comments1 min readLW link

Summaries of top forum posts (24th − 30th April 2023)

Zoe WilliamsMay 2, 2023, 2:30 AM

12 points

1 comment1 min readLW link

EA & LW Forum Weekly Summary (30th Jan − 5th Feb 2023)

Zoe WilliamsFeb 7, 2023, 2:13 AM

3 points

3 comments1 min readLW link

AI Safety Newsletter #4: AI and Cybersecurity, Persuasive AIs, Weaponization, and Geoffrey Hinton talks AI risks

ozhang and Dan H

May 2, 2023, 6:41 PM

32 points

0 comments5 min readLW link

(newsletter.safe.ai)

AISN #31: A New AI Policy Bill in California Plus, Precedents for AI Governance and The EU AI Office

Dan HFeb 21, 2024, 9:58 PM

17 points

0 comments6 min readLW link

(newsletter.safe.ai)

EA & LW Forum Weekly Summary (27th Feb − 5th Mar 2023)

Zoe WilliamsMar 6, 2023, 3:18 AM

12 points

0 comments1 min readLW link

AI #102: Made in America

ZviFeb 6, 2025, 2:20 PM

26 points

17 comments67 min readLW link

(thezvi.wordpress.com)

EA & LW Forum Weekly Summary (6th − 12th March 2023)

Zoe WilliamsMar 14, 2023, 3:01 AM

7 points

0 comments1 min readLW link

AI #10: Code Interpreter and Geoff Hinton

ZviMay 4, 2023, 2:00 PM

80 points

7 comments78 min readLW link

(thezvi.wordpress.com)

AI Safety − 7 months of discussion in 17 minutes

Zoe WilliamsMar 15, 2023, 11:41 PM

25 points

0 comments1 min readLW link

Forecasting newsletter #2/2025: Forecasting meetup network

NunoSempereFeb 9, 2025, 6:07 PM

13 points

0 comments4 min readLW link

(forecasting.substack.com)

EA & LW Forum Weekly Summary (13th − 19th March 2023)

Zoe WilliamsMar 20, 2023, 4:18 AM

13 points

0 comments1 min readLW link

AI Safety at the Frontier: Paper Highlights, January ’25

gasteigerjoFeb 11, 2025, 4:14 PM

7 points

0 comments8 min readLW link

(aisafetyfrontier.substack.com)

Summaries of top forum posts (1st to 7th May 2023)

Zoe WilliamsMay 9, 2023, 9:30 AM

21 points

0 comments1 min readLW link

AI Safety Newsletter #5: Geoffrey Hinton speaks out on AI risk, the White House meets with AI labs, and Trojan attacks on language models

Dan HMay 9, 2023, 3:26 PM

28 points

1 comment4 min readLW link

(newsletter.safe.ai)

AI #11: In Search of a Moat

ZviMay 11, 2023, 3:40 PM

67 points

28 comments81 min readLW link

(thezvi.wordpress.com)

AI Safety Newsletter #6: Examples of AI safety progress, Yoshua Bengio proposes a ban on AI agents, and lessons from nuclear arms control

Dan HMay 16, 2023, 3:14 PM

31 points

0 comments6 min readLW link

(newsletter.safe.ai)

March gwern.net link roundup

gwernApr 20, 2018, 7:09 PM

10 points

1 comment1 min readLW link

(www.gwern.net)

Announcing Rational Newsletter

Alexey LapitskyApr 1, 2018, 2:37 PM

10 points

9 comments1 min readLW link

Recent updates to gwern.net (2013-2014)

gwernJul 8, 2014, 1:44 AM

38 points

32 comments4 min readLW link

Announcing LessWrong Digest

Evan_GaensbauerFeb 23, 2015, 10:41 AM

35 points

18 comments1 min readLW link

July 2020 gwern.net newsletter

gwernAug 20, 2020, 4:39 PM

29 points

0 comments1 min readLW link

(www.gwern.net)

[AN #113]: Checking the ethical intuitions of large language models

Rohin ShahAug 19, 2020, 5:10 PM

23 points

0 comments9 min readLW link

(mailchi.mp)

Progress Studies Fellowship looking for members

jay ramJul 6, 2023, 5:41 PM

3 points

0 comments1 min readLW link

July 2019 gwern.net newsletter

gwernAug 1, 2019, 4:19 PM

23 points

0 comments1 min readLW link

(www.gwern.net)

June 2020 gwern.net newsletter

gwernJul 2, 2020, 2:19 PM

16 points

0 comments1 min readLW link

(www.gwern.net)

May Gwern.net newsletter (w/GPT-3 commentary)

gwernJun 2, 2020, 3:40 PM

32 points

7 comments1 min readLW link

(www.gwern.net)

April 2020 gwern.net newsletter

gwernMay 1, 2020, 8:47 PM

11 points

0 comments1 min readLW link

(www.gwern.net)

March 2020 gwern.net newsletter

gwernApr 3, 2020, 2:16 AM

13 points

1 comment1 min readLW link

(www.gwern.net)

February 2020 gwern.net newsletter

gwernMar 4, 2020, 7:05 PM

15 points

0 comments1 min readLW link

(www.gwern.net)

January 2020 gwern.net newsletter

gwernJan 31, 2020, 6:04 PM

19 points

0 comments1 min readLW link

(www.gwern.net)

July gwern.net newsletter

gwernAug 2, 2018, 1:42 PM

24 points

0 comments1 min readLW link

(www.gwern.net)

[AN #114]: Theory-inspired safety solutions for powerful Bayesian RL agents

Rohin ShahAug 26, 2020, 5:20 PM

21 points

3 comments8 min readLW link

(mailchi.mp)

Bi-Weekly Rational Feed

sapphireJun 24, 2017, 12:07 AM

35 points

3 comments12 min readLW link

September 2019 gwern.net newsletter

gwernOct 4, 2019, 4:44 PM

21 points

0 comments1 min readLW link

(www.gwern.net)

Russian x-risks newsletter Summer 2020

avturchinSep 1, 2020, 2:06 PM

22 points

6 comments1 min readLW link

Forecasting Newsletter: August 2020.

NunoSempereSep 1, 2020, 11:38 AM

16 points

1 comment6 min readLW link

August 2020 gwern.net newsletter

gwernSep 1, 2020, 9:04 PM

25 points

4 comments1 min readLW link

(www.gwern.net)

AI Impacts Quarterly Newsletter, Apr-Jun 2023

Harlan and Richard Korzekwa

Jul 18, 2023, 5:14 PM

6 points

0 comments3 min readLW link

(blog.aiimpacts.org)

Russian x-risks newsletter #2, fall 2019

avturchinDec 3, 2019, 4:54 PM

22 points

0 comments3 min readLW link

[AN #116]: How to make explanations of neurons compositional

Rohin ShahSep 9, 2020, 5:20 PM

21 points

2 comments9 min readLW link

(mailchi.mp)

Manifund: What we’re funding (weeks 2-4)

Austin ChenAug 4, 2023, 4:00 PM

44 points

2 comments1 min readLW link

(manifund.substack.com)

AISN #19: US-China Competition on AI Chips, Measuring Language Agent Developments, Economic Analysis of Language Model Propaganda, and White House AI Cyber Challenge

Dan HAug 15, 2023, 4:10 PM

21 points

0 comments5 min readLW link

(newsletter.safe.ai)

Dec 2019 gwern.net newsletter

gwernJan 4, 2020, 8:48 PM

17 points

2 comments1 min readLW link

(www.gwern.net)

Recent updates to gwern.net (2014-2015)

gwernNov 2, 2015, 12:06 AM

34 points

3 comments3 min readLW link

[AN #123]: Inferring what is valuable in order to align recommender systems

Rohin ShahOct 28, 2020, 5:00 PM

20 points

1 comment8 min readLW link

(mailchi.mp)

September 2020 gwern.net newsletter

gwernOct 26, 2020, 1:38 PM

17 points

1 comment1 min readLW link

(www.gwern.net)

May gwern.net newsletter

gwernJun 1, 2019, 5:25 PM

17 points

0 comments1 min readLW link

(www.gwern.net)

March 2019 gwern.net newsletter

gwernApr 2, 2019, 2:17 PM

19 points

9 comments1 min readLW link

(www.gwern.net)

December gwern.net newsletter

gwernJan 2, 2019, 3:13 PM

20 points

0 comments1 min readLW link

(www.gwern.net)

AISN #20: LLM Proliferation, AI Deception, and Continuing Drivers of AI Capabilities

Dan HAug 29, 2023, 3:07 PM

12 points

0 comments8 min readLW link

(newsletter.safe.ai)

Forecasting Newsletter: October 2020.

NunoSempereNov 1, 2020, 1:09 PM

11 points

0 comments4 min readLW link

AI #27: Portents of Gemini

ZviAug 31, 2023, 12:40 PM

54 points

37 comments47 min readLW link

(thezvi.wordpress.com)

January 2019 gwern.net newsletter

gwernFeb 4, 2019, 3:53 PM

15 points

0 comments1 min readLW link

(www.gwern.net)

Bi-weekly Rational Feed

sapphireAug 8, 2017, 1:56 PM

29 points

4 comments13 min readLW link

AISN #21: Google DeepMind’s GPT-4 Competitor, Military Investments in Autonomous Drones, The UK AI Safety Summit, and Case Studies in AI Policy

Dan HSep 5, 2023, 3:03 PM

15 points

0 comments5 min readLW link

(newsletter.safe.ai)

[AN #125]: Neural network scaling laws across multiple modalities

Rohin ShahNov 11, 2020, 6:20 PM

25 points

7 comments9 min readLW link

(mailchi.mp)

MLSN: #10 Adversarial Attacks Against Language and Vision Models, Improving LLM Honesty, and Tracing the Influence of LLM Training Data

Sep 13, 2023, 6:03 PM

15 points

1 comment5 min readLW link

(newsletter.mlsafety.org)

AISN #22: The Landscape of US AI Legislation - Hearings, Frameworks, Bills, and Laws

Dan HSep 19, 2023, 2:44 PM

20 points

0 comments5 min readLW link

(newsletter.safe.ai)

[AN #127]: Rethinking agency: Cartesian frames as a formalization of ways to carve up the world into an agent and its environment

Rohin ShahDec 2, 2020, 6:20 PM

53 points

0 comments13 min readLW link

(mailchi.mp)

November 2020 gwern.net newsletter

gwernDec 3, 2020, 10:47 PM

14 points

5 comments1 min readLW link

(www.gwern.net)

[AN #133]: Building machines that can cooperate (with humans, institutions, or other machines)

Rohin ShahJan 13, 2021, 6:10 PM

14 points

0 comments9 min readLW link

(mailchi.mp)

[AN #136]: How well will GPT-N perform on downstream tasks?

Rohin ShahFeb 3, 2021, 6:10 PM

21 points

2 comments9 min readLW link

(mailchi.mp)

[AN #172] Sorry for the long hiatus!

Rohin ShahJul 5, 2022, 6:20 AM

54 points

0 comments3 min readLW link

(mailchi.mp)

EA & LW Forums Weekly Summary (28 Aug − 3 Sep 22’)

Zoe WilliamsSep 6, 2022, 11:06 AM

51 points

2 comments14 min readLW link

EA & LW Forums Weekly Summary (26 Sep − 9 Oct 22′)

Zoe WilliamsOct 10, 2022, 11:58 PM

13 points

2 comments1 min readLW link

Newsletter for Alignment Research: The ML Safety Updates

Esben KranOct 22, 2022, 4:17 PM

25 points

0 comments1 min readLW link

NeurIPS Safety & ChatGPT. MLAISU W48

Esben Kran and Steinthal

Dec 2, 2022, 3:50 PM

3 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

Will Machines Ever Rule the World? MLAISU W50

Esben KranDec 16, 2022, 11:03 AM

12 points

7 comments4 min readLW link

(newsletter.apartresearch.com)

EA & LW Forums Weekly Summary (12th Dec − 18th Dec 22′)

Zoe WilliamsDec 20, 2022, 9:49 AM

10 points

0 comments1 min readLW link

AI improving AI [MLAISU W01!]

Esben KranJan 6, 2023, 11:13 AM

5 points

0 comments4 min readLW link

(newsletter.apartresearch.com)

[MLSN #7]: an example of an emergent internal optimizer

joshc and Dan H

Jan 9, 2023, 7:39 PM

28 points

0 comments6 min readLW link

Robustness & Evolution [MLAISU W02]

Esben KranJan 13, 2023, 3:47 PM

10 points

0 comments3 min readLW link

(newsletter.apartresearch.com)

Generalizability & Hope for AI [MLAISU W03]

Esben KranJan 20, 2023, 10:06 AM

5 points

2 comments2 min readLW link

(newsletter.apartresearch.com)

November 2018 gwern.net newsletter

gwernDec 1, 2018, 1:57 PM

35 points

0 comments1 min readLW link

(www.gwern.net)

AI Safety Newsletter #40: California AI Legislation Plus, NVIDIA Delays Chip Production, and Do AI Safety Benchmarks Actually Measure Safety?

Corin Katzke, Julius, Alexa Pan and Dan H

Aug 21, 2024, 6:09 PM

11 points

0 comments6 min readLW link

(newsletter.safe.ai)

MIRI’s April 2024 Newsletter

HarlanApr 12, 2024, 11:38 PM

95 points

0 comments3 min readLW link

(intelligence.org)

AISN #36: Voluntary Commitments are Insufficient Plus, a Senate AI Policy Roadmap, and Chapter 1: An Overview of Catastrophic Risks

Corin Katzke, Julius and Dan H

Jun 5, 2024, 5:45 PM

9 points

0 comments5 min readLW link

(newsletter.safe.ai)

Weekly newsletter for AI safety events and training programs

Bryce RobertsonMay 3, 2024, 12:33 AM

29 points

0 comments1 min readLW link

MIRI’s June 2024 Newsletter

HarlanJun 14, 2024, 11:02 PM

74 points

20 comments2 min readLW link

(intelligence.org)

AI Safety Newsletter #37: US Launches Antitrust Investigations Plus, recent criticisms of OpenAI and Anthropic, and a summary of Situational Awareness

Corin Katzke, Alexa Pan, Julius and Dan H

Jun 18, 2024, 6:07 PM

8 points

0 comments5 min readLW link

(newsletter.safe.ai)

AI Safety Newsletter #41: The Next Generation of Compute Scale Plus, Ranking Models by Susceptibility to Jailbreaking, and Machine Ethics

Corin Katzke, Corin Katzke, Julius, andrewz and Dan H

Sep 11, 2024, 7:14 PM

5 points

1 comment5 min readLW link

(newsletter.safe.ai)

AISN #38: Supreme Court Decision Could Limit Federal Ability to Regulate AI Plus, “Circuit Breakers” for AI systems, and updates on China’s AI industry

Corin Katzke, Alexa Pan, Julius and Dan H

Jul 9, 2024, 7:28 PM

5 points

0 comments5 min readLW link

(newsletter.safe.ai)

MIRI’s July 2024 newsletter

HarlanJul 15, 2024, 9:28 PM

25 points

2 comments1 min readLW link

(intelligence.org)

AISN #45: Center for AI Safety 2024 Year in Review

Corin Katzke and Dan H

Dec 19, 2024, 6:15 PM

13 points

0 comments4 min readLW link

(newsletter.safe.ai)

AI Safety Newsletter #39: Implications of a Trump Administration for AI Policy Plus, Safety Engineering

Corin Katzke, Alexa Pan, Julius and Dan H

Jul 29, 2024, 5:50 PM

17 points

1 comment6 min readLW link

(newsletter.safe.ai)

AI Safety Newsletter #42: Newsom Vetoes SB 1047 Plus, OpenAI’s o1, and AI Governance Summary

Corin Katzke, Corin Katzke, Julius, Alexa Pan, andrewz and Dan H

Oct 1, 2024, 8:35 PM

8 points

0 comments6 min readLW link

(newsletter.safe.ai)

Launching Adjacent News

Lucas KohorstOct 16, 2024, 5:58 PM

24 points

0 comments4 min readLW link

AISN #44: The Trump Circle on AI Safety Plus, Chinese researchers used Llama to create a military tool for the PLA, a Google AI system discovered a zero-day cybersecurity vulnerability, and Complex Systems

Corin Katzke, Julius, andrewz and Dan H

Nov 19, 2024, 4:36 PM

9 points

0 comments5 min readLW link

(newsletter.safe.ai)

AISN #49: Superintelligence Strategy

Corin Katzke and Dan H

Mar 6, 2025, 5:46 PM

6 points

1 comment5 min readLW link

(newsletter.safe.ai)

AISN #46: The Transition

Corin Katzke and Dan H

Jan 23, 2025, 6:09 PM

8 points

0 comments5 min readLW link

(newsletter.safe.ai)

AISN #47: Reasoning Models

Corin Katzke and Dan H

Feb 6, 2025, 6:52 PM

3 points

0 comments4 min readLW link

(newsletter.safe.ai)

AI Safety Newsletter #2: ChaosGPT, Natural Selection, and AI Safety in the Media

ozhang and Dan H

Apr 18, 2023, 6:44 PM

30 points

0 comments4 min readLW link

(newsletter.safe.ai)

What I’ve been reading, November 2023

jasoncrawfordNov 7, 2023, 1:37 PM

23 points

1 comment5 min readLW link

(rootsofprogress.org)

OpenAI: Facts from a Weekend

ZviNov 20, 2023, 3:30 PM

271 points

165 comments9 min readLW link

(thezvi.wordpress.com)

Forecasting Newsletter: April 2020

NunoSempereApr 30, 2020, 4:41 PM

22 points

3 comments6 min readLW link

Forecasting Newsletter: May 2020.

NunoSempereMay 31, 2020, 12:35 PM

9 points

1 comment20 min readLW link

Null-boxing Newcomb’s Problem

YitzJul 13, 2020, 4:32 PM

33 points

9 comments4 min readLW link

May gwern.net newsletter

gwernJun 1, 2018, 2:47 PM

24 points

3 comments1 min readLW link

(www.gwern.net)

Rationality Feed: Last Month’s Best Posts

sapphireFeb 12, 2018, 1:18 PM

23 points

1 comment3 min readLW link

Alignment Newsletter #13: 07/02/18

Rohin ShahJul 2, 2018, 4:10 PM

70 points

12 comments8 min readLW link

(mailchi.mp)

Alignment Newsletter #16: 07/23/18

Rohin ShahJul 23, 2018, 4:20 PM

42 points

0 comments12 min readLW link

(mailchi.mp)

Alignment Newsletter #15: 07/16/18

Rohin ShahJul 16, 2018, 4:10 PM

42 points

0 comments15 min readLW link

(mailchi.mp)

[AN #58] Mesa optimization: what it is, and why we should care

Rohin ShahJun 24, 2019, 4:10 PM

55 points

10 comments8 min readLW link

(mailchi.mp)

Rationality Feed: Last Month’s Best Posts

sapphireMar 21, 2018, 2:12 PM

20 points

2 comments2 min readLW link

[AN #59] How arguments for AI risk have changed over time

Rohin ShahJul 8, 2019, 5:20 PM

43 points

4 comments7 min readLW link

(mailchi.mp)

The Alignment Newsletter #1: 04/09/18

Rohin ShahApr 9, 2018, 4:00 PM

12 points

3 comments4 min readLW link

The Alignment Newsletter #2: 04/16/18

Rohin ShahApr 16, 2018, 4:00 PM

8 points

0 comments5 min readLW link

The Alignment Newsletter #3: 04/23/18

Rohin ShahApr 23, 2018, 4:00 PM

9 points

0 comments6 min readLW link

The Alignment Newsletter #4: 04/30/18

Rohin ShahApr 30, 2018, 4:00 PM

8 points

0 comments3 min readLW link

The Alignment Newsletter #5: 05/07/18

Rohin ShahMay 7, 2018, 4:00 PM

8 points

0 comments7 min readLW link

The Alignment Newsletter #6: 05/14/18

Rohin ShahMay 14, 2018, 4:00 PM

8 points

0 comments2 min readLW link

The Alignment Newsletter #7: 05/21/18

Rohin ShahMay 21, 2018, 4:00 PM

8 points

0 comments5 min readLW link

The Alignment Newsletter #8: 05/28/18

Rohin ShahMay 28, 2018, 4:00 PM

8 points

0 comments6 min readLW link

The Alignment Newsletter #9: 06/04/18

Rohin ShahJun 4, 2018, 4:00 PM

8 points

0 comments2 min readLW link

The Alignment Newsletter #10: 06/11/18

Rohin ShahJun 11, 2018, 4:00 PM

16 points

0 comments9 min readLW link

The Alignment Newsletter #11: 06/18/18

Rohin ShahJun 18, 2018, 4:00 PM

8 points

0 comments10 min readLW link

The Alignment Newsletter #12: 06/25/18

Rohin ShahJun 25, 2018, 4:00 PM

15 points

0 comments3 min readLW link

Alignment Newsletter #14

Rohin ShahJul 9, 2018, 4:20 PM

14 points

0 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #17

Rohin ShahJul 30, 2018, 4:10 PM

32 points

0 comments13 min readLW link

(mailchi.mp)

Alignment Newsletter #18

Rohin ShahAug 6, 2018, 4:00 PM

17 points

0 comments10 min readLW link

(mailchi.mp)

Alignment Newsletter #19

Rohin ShahAug 14, 2018, 2:10 AM

18 points

0 comments13 min readLW link

(mailchi.mp)

Alignment Newsletter #20

Rohin ShahAug 20, 2018, 4:00 PM

12 points

2 comments6 min readLW link

(mailchi.mp)

Alignment Newsletter #21

Rohin ShahAug 27, 2018, 4:20 PM

25 points

0 comments7 min readLW link

(mailchi.mp)

Alignment Newsletter #22

Rohin ShahSep 3, 2018, 4:10 PM

18 points

0 comments6 min readLW link

(mailchi.mp)

Alignment Newsletter #23

Rohin ShahSep 10, 2018, 5:10 PM

16 points

0 comments7 min readLW link

(mailchi.mp)

Alignment Newsletter #24

Rohin ShahSep 17, 2018, 4:20 PM

10 points

6 comments12 min readLW link

(mailchi.mp)

Alignment Newsletter #25

Rohin ShahSep 24, 2018, 4:10 PM

18 points

3 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #26

Rohin ShahOct 2, 2018, 4:10 PM

13 points

0 comments7 min readLW link

(mailchi.mp)

Alignment Newsletter #27

Rohin ShahOct 9, 2018, 1:10 AM

16 points

0 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #28

Rohin ShahOct 15, 2018, 9:20 PM

11 points

0 comments8 min readLW link

(mailchi.mp)

Alignment Newsletter #29

Rohin ShahOct 22, 2018, 4:20 PM

15 points

0 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #30

Rohin ShahOct 29, 2018, 4:10 PM

29 points

2 comments6 min readLW link

(mailchi.mp)

Alignment Newsletter #31

Rohin ShahNov 5, 2018, 11:50 PM

17 points

0 comments12 min readLW link

(mailchi.mp)

Alignment Newsletter #32

Rohin ShahNov 12, 2018, 5:20 PM

18 points

0 comments12 min readLW link

(mailchi.mp)

Alignment Newsletter #33

Rohin ShahNov 19, 2018, 5:20 PM

23 points

0 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #34

Rohin ShahNov 26, 2018, 11:10 PM

24 points

0 comments10 min readLW link

(mailchi.mp)

Alignment Newsletter #35

Rohin ShahDec 4, 2018, 1:10 AM

15 points

0 comments6 min readLW link

(mailchi.mp)

Alignment Newsletter #37

Rohin ShahDec 17, 2018, 7:10 PM

25 points

4 comments10 min readLW link

(mailchi.mp)

Alignment Newsletter #38

Rohin ShahDec 25, 2018, 4:10 PM

9 points

0 comments8 min readLW link

(mailchi.mp)

Alignment Newsletter #39

Rohin ShahJan 1, 2019, 8:10 AM

32 points

2 comments5 min readLW link

(mailchi.mp)

Alignment Newsletter #40

Rohin ShahJan 8, 2019, 8:10 PM

21 points

2 comments5 min readLW link

(mailchi.mp)

Alignment Newsletter #41

Rohin ShahJan 17, 2019, 8:10 AM

22 points

6 comments10 min readLW link

(mailchi.mp)

Alignment Newsletter #42

Rohin ShahJan 22, 2019, 2:00 AM

20 points

1 comment10 min readLW link

(mailchi.mp)

Alignment Newsletter #43

Rohin ShahJan 29, 2019, 9:10 PM

14 points

2 comments13 min readLW link

(mailchi.mp)

Alignment Newsletter #44

Rohin ShahFeb 6, 2019, 8:30 AM

18 points

0 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #45

Rohin ShahFeb 14, 2019, 2:10 AM

25 points

2 comments8 min readLW link

(mailchi.mp)

Alignment Newsletter #46

Rohin ShahFeb 22, 2019, 12:10 AM

12 points

0 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #48

Rohin ShahMar 11, 2019, 9:10 PM

29 points

14 comments9 min readLW link

(mailchi.mp)

Alignment Newsletter #49

Rohin ShahMar 20, 2019, 4:20 AM

23 points

1 comment11 min readLW link

(mailchi.mp)

Alignment Newsletter #50

Rohin ShahMar 28, 2019, 6:10 PM

15 points

2 comments10 min readLW link

(mailchi.mp)

Alignment Newsletter #51

Rohin ShahApr 3, 2019, 4:10 AM

25 points

2 comments15 min readLW link

(mailchi.mp)

Alignment Newsletter #52

Rohin ShahApr 6, 2019, 1:20 AM

19 points

1 comment8 min readLW link

(mailchi.mp)

Alignment Newsletter One Year Retrospective

Rohin ShahApr 10, 2019, 6:58 AM

94 points

31 comments21 min readLW link

Alignment Newsletter #53

Rohin ShahApr 18, 2019, 5:20 PM

20 points

0 comments8 min readLW link

(mailchi.mp)

[AN #54] Boxing a finite-horizon AI system to keep it unambitious

Rohin ShahApr 28, 2019, 5:20 AM

20 points

0 comments8 min readLW link

(mailchi.mp)

[AN #55] Regulatory markets and international standards as a means of ensuring beneficial AI

Rohin ShahMay 5, 2019, 2:20 AM

17 points

2 comments8 min readLW link

(mailchi.mp)

[AN #56] Should ML researchers stop running experiments before making hypotheses?

Rohin ShahMay 21, 2019, 2:20 AM

21 points

8 comments9 min readLW link

(mailchi.mp)

[AN #57] Why we should focus on robustness in AI safety, and the analogous problems in programming

Rohin ShahJun 5, 2019, 11:20 PM

26 points

15 comments7 min readLW link

(mailchi.mp)

[AN #60] A new AI challenge: Minecraft agents that assist human players in creative mode

Rohin ShahJul 22, 2019, 5:00 PM

23 points

6 comments9 min readLW link

(mailchi.mp)

[AN #61] AI policy and governance, from two people in the field

Rohin ShahAug 5, 2019, 5:00 PM

12 points

2 comments9 min readLW link

(mailchi.mp)

[AN #62] Are adversarial examples caused by real but imperceptible features?

Rohin ShahAug 22, 2019, 5:10 PM

28 points

10 comments9 min readLW link

(mailchi.mp)

[AN #63] How architecture search, meta learning, and environment design could lead to general intelligence

Rohin ShahSep 10, 2019, 7:10 PM

21 points

12 comments8 min readLW link

(mailchi.mp)

[AN #64]: Using Deep RL and Reward Uncertainty to Incentivize Preference Learning

Rohin ShahSep 16, 2019, 5:10 PM

11 points

8 comments7 min readLW link

(mailchi.mp)

[AN #65]: Learning useful skills by watching humans “play”

Rohin ShahSep 23, 2019, 5:30 PM

11 points

0 comments9 min readLW link

(mailchi.mp)

[AN #66]: Decomposing robustness into capability robustness and alignment robustness

Rohin ShahSep 30, 2019, 6:00 PM

12 points

1 comment7 min readLW link

(mailchi.mp)

[AN #67]: Creating environments in which to study inner alignment failures

Rohin ShahOct 7, 2019, 5:10 PM

17 points

0 comments8 min readLW link

(mailchi.mp)

[AN #68]: The attainable utility theory of impact

Rohin ShahOct 14, 2019, 5:00 PM

17 points

0 comments8 min readLW link

(mailchi.mp)

[AN #69] Stuart Russell’s new book on why we need to replace the standard model of AI

Rohin ShahOct 19, 2019, 12:30 AM

60 points

12 comments15 min readLW link

(mailchi.mp)

[AN #70]: Agents that help humans who are still learning about their own preferences

Rohin ShahOct 23, 2019, 5:10 PM

16 points

0 comments9 min readLW link

(mailchi.mp)

[AN #71]: Avoiding reward tampering through current-RF optimization

Rohin ShahOct 30, 2019, 5:10 PM

12 points

0 comments7 min readLW link

(mailchi.mp)

[AN #72]: Alignment, robustness, methodology, and system building as research priorities for AI safety

Rohin ShahNov 6, 2019, 6:10 PM

26 points

4 comments10 min readLW link

(mailchi.mp)

[AN #73]: Detecting catastrophic failures by learning how agents tend to break

Rohin ShahNov 13, 2019, 6:10 PM

11 points

0 comments7 min readLW link

(mailchi.mp)

[AN #74]: Separating beneficial AI into competence, alignment, and coping with impacts

Rohin ShahNov 20, 2019, 6:20 PM

19 points

0 comments7 min readLW link

(mailchi.mp)

[AN #75]: Solving Atari and Go with learned game models, and thoughts from a MIRI employee

Rohin ShahNov 27, 2019, 6:10 PM

38 points

1 comment10 min readLW link

(mailchi.mp)

[AN #76]: How dataset size affects robustness, and benchmarking safe exploration by measuring constraint violations

Rohin ShahDec 4, 2019, 6:10 PM

14 points

6 comments9 min readLW link

(mailchi.mp)

[AN #77]: Double descent: a unification of statistical theory and modern ML practice

Rohin ShahDec 18, 2019, 6:30 PM

21 points

4 comments14 min readLW link

(mailchi.mp)

[AN #78] Formalizing power and instrumental convergence, and the end-of-year AI safety charity comparison

Rohin ShahDec 26, 2019, 1:10 AM

26 points

10 comments9 min readLW link

(mailchi.mp)

[AN #79]: Recursive reward modeling as an alignment technique integrated with deep RL

Rohin ShahJan 1, 2020, 6:00 PM

13 points

0 comments12 min readLW link

(mailchi.mp)

[AN #80]: Why AI risk might be solved without additional intervention from longtermists

Rohin ShahJan 2, 2020, 6:20 PM

36 points

95 comments10 min readLW link

(mailchi.mp)

[AN #81]: Universality as a potential solution to conceptual difficulties in intent alignment

Rohin ShahJan 8, 2020, 6:00 PM

32 points

4 comments11 min readLW link

(mailchi.mp)

[AN #82]: How OpenAI Five distributed their training computation

Rohin ShahJan 15, 2020, 6:20 PM

19 points

0 comments8 min readLW link

(mailchi.mp)

[AN #83]: Sample-efficient deep learning with ReMixMatch

Rohin ShahJan 22, 2020, 6:10 PM

15 points

4 comments11 min readLW link

(mailchi.mp)

[AN #84] Reviewing AI alignment work in 2018-19

Rohin ShahJan 29, 2020, 6:30 PM

23 points

0 comments6 min readLW link

(mailchi.mp)

[AN #85]: The normative questions we should be asking for AI alignment, and a surprisingly good chatbot

Rohin ShahFeb 5, 2020, 6:20 PM

14 points

2 comments7 min readLW link

(mailchi.mp)

[AN #86]: Improving debate and factored cognition through human experiments

Rohin ShahFeb 12, 2020, 6:10 PM

15 points

0 comments9 min readLW link

(mailchi.mp)

[AN #87]: What might happen as deep learning scales even further?

Rohin ShahFeb 19, 2020, 6:20 PM

28 points

0 comments4 min readLW link

(mailchi.mp)

[AN #88]: How the principal-agent literature relates to AI risk

Rohin ShahFeb 27, 2020, 9:10 AM

18 points

0 comments9 min readLW link

(mailchi.mp)

[AN #89]: A unifying formalism for preference learning algorithms

Rohin ShahMar 4, 2020, 6:20 PM

16 points

0 comments9 min readLW link

(mailchi.mp)

[AN #90]: How search landscapes can contain self-reinforcing feedback loops

Rohin ShahMar 11, 2020, 5:30 PM

11 points

6 comments8 min readLW link

(mailchi.mp)

[AN #91]: Concepts, implementations, problems, and a benchmark for impact measurement

Rohin ShahMar 18, 2020, 5:10 PM

15 points

10 comments13 min readLW link

(mailchi.mp)

[AN #92]: Learning good representations with contrastive predictive coding

Rohin ShahMar 25, 2020, 5:20 PM

18 points

1 comment10 min readLW link

(mailchi.mp)

[AN #93]: The Precipice we’re standing at, and how we can back away from it

Rohin ShahApr 1, 2020, 5:10 PM

24 points

0 comments7 min readLW link

(mailchi.mp)

[AN #94]: AI alignment as translation between humans and machines

Rohin ShahApr 8, 2020, 5:10 PM

11 points

0 comments7 min readLW link

(mailchi.mp)

[AN #95]: A framework for thinking about how to make AI go well

Rohin ShahApr 15, 2020, 5:10 PM

20 points

2 comments10 min readLW link

(mailchi.mp)

[AN #96]: Buck and I discuss/argue about AI Alignment

Rohin ShahApr 22, 2020, 5:20 PM

17 points

4 comments10 min readLW link

(mailchi.mp)

[AN #97]: Are there historical examples of large, robust discontinuities?

Rohin ShahApr 29, 2020, 5:30 PM

15 points

0 comments10 min readLW link

(mailchi.mp)

[AN #98]: Understanding neural net training by seeing which gradients were helpful

Rohin ShahMay 6, 2020, 5:10 PM

22 points

3 comments9 min readLW link

(mailchi.mp)

[AN #99]: Doubling times for the efficiency of AI algorithms

Rohin ShahMay 13, 2020, 5:20 PM

29 points

0 comments10 min readLW link

(mailchi.mp)

[AN #100]: What might go wrong if you learn a reward function while acting

Rohin ShahMay 20, 2020, 5:30 PM

33 points

2 comments12 min readLW link

(mailchi.mp)

[AN #101]: Why we should rigorously measure and forecast AI progress

Rohin ShahMay 27, 2020, 5:20 PM

15 points

0 comments10 min readLW link

(mailchi.mp)

[AN #103]: ARCHES: an agenda for existential safety, and combining natural language with deep RL

Rohin ShahJun 10, 2020, 5:20 PM

29 points

0 comments10 min readLW link

(mailchi.mp)

[AN #104]: The perils of inaccessible information, and what we can learn about AI alignment from COVID

Rohin ShahJun 18, 2020, 5:10 PM

19 points

5 comments8 min readLW link

(mailchi.mp)

[AN #105]: The economic trajectory of humanity, and what we might mean by optimization

Rohin ShahJun 24, 2020, 5:30 PM

24 points

3 comments11 min readLW link

(mailchi.mp)

[AN #106]: Evaluating generalization ability of learned reward models

Rohin ShahJul 1, 2020, 5:20 PM

14 points

2 comments11 min readLW link

(mailchi.mp)

[AN #107]: The convergent instrumental subgoals of goal-directed agents

Rohin ShahJul 16, 2020, 6:47 AM

13 points

1 comment8 min readLW link

(mailchi.mp)

[AN #108]: Why we should scrutinize arguments for AI risk

Rohin ShahJul 16, 2020, 6:47 AM

19 points

6 comments12 min readLW link

(mailchi.mp)

[AN #109]: Teaching neural nets to generalize the way humans would

Rohin ShahJul 22, 2020, 5:10 PM

17 points

3 comments9 min readLW link

(mailchi.mp)

[AN #110]: Learning features from human feedback to enable reward learning

Rohin ShahJul 29, 2020, 5:20 PM

13 points

2 comments10 min readLW link

(mailchi.mp)

Regulate or Compete? The China Factor in U.S. AI Policy (NAIR #2)

charles_mMay 5, 2023, 5:43 PM

2 points

1 comment7 min readLW link

(navigatingairisks.substack.com)

Russian x-risks newsletter, summer 2019

avturchinSep 7, 2019, 9:50 AM

39 points

5 comments4 min readLW link

Rational Feed: Last Month’s Best Posts

sapphireMay 2, 2018, 6:19 PM

16 points

0 comments2 min readLW link

Forecasting Newsletter: July 2020.

NunoSempereAug 1, 2020, 5:08 PM

21 points

4 comments22 min readLW link

June gwern.net newsletter

gwernJul 4, 2018, 10:59 PM

34 points

0 comments1 min readLW link

(www.gwern.net)

[AN #111]: The Circuits hypotheses for deep learning

Rohin ShahAug 5, 2020, 5:40 PM

23 points

0 comments9 min readLW link

(mailchi.mp)

Call for contributors to the Alignment Newsletter

Rohin ShahAug 21, 2019, 6:21 PM

39 points

0 comments4 min readLW link

June 2019 gwern.net newsletter

gwernJul 1, 2019, 2:35 PM

29 points

0 comments1 min readLW link

(www.gwern.net)

Recent updates to gwern.net (2015-2016)

gwernAug 26, 2016, 7:22 PM

42 points

6 comments1 min readLW link

Recent updates to gwern.net (2011)

gwernNov 26, 2011, 1:58 AM

45 points

18 comments1 min readLW link

October gwern.net links

gwernNov 1, 2018, 1:11 AM

29 points

8 comments1 min readLW link

(www.gwern.net)

No comments.

Keyboard shortcuts

Keys shown in yellow (e.g., ]) are accesskeys, and require a browser-specific modifier key (or keys).

Keys shown in grey (e.g., ?) do not require any modifier keys.

General
? Show keyboard shortcuts
Esc Hide keyboard shortcuts

Site navigation
h Go to Home (a.k.a. “Frontpage”) view
f Go to Featured (a.k.a. “Curated”) view
a Go to All (a.k.a. “Community”) view
m Go to Meta view
v Go to Tags view
c Go to Recent Comments view
r Go to Archive view
q Go to Sequences view
t Go to About page
u Go to User or Login page
o Go to Inbox page

Page navigation
, Jump up to top of page
. Jump down to bottom of page
/ Jump to top of comments section
s Search

Page actions
n New post or comment
e Edit current post

Post/comment list views
. Focus next entry in list
, Focus previous entry in list
; Cycle between links in focused entry
Enter Go to currently focused entry
Esc Unfocus currently focused entry
] Go to next page
[ Go to previous page
\ Go to first page
e Edit currently focused post

Editor
k Bold text
i Italic text
l Insert hyperlink
q Blockquote text

Appearance
= Increase text size
- Decrease text size
0 Reset to default text size
′ Cycle through content width settings
1 Switch to default theme [A]
2 Switch to dark theme [B]
3 Switch to grey theme [C]
4 Switch to ultramodern theme [D]
5 Switch to simple theme [E]
6 Switch to brutalist theme [F]
7 Switch to ReadTheSequences theme [G]
8 Switch to classic Less Wrong theme [H]
9 Switch to modern Less Wrong theme [I]
; Open theme tweaker
Enter Save changes and close theme tweaker
Esc Close theme tweaker (without saving)

Slide shows
l Start/resume slideshow
Esc Exit slideshow
→↓ Next slide
←↑ Previous slide
Space Reset slide zoom

Miscellaneous
x Switch to next view on user page
z Switch to previous view on user page
` Toggle compact comment list view
g Toggle anti-kibitzer