DeepMind’s “Frontier Safety Framework” is weak and unambitious

Zach Stein-Perlman18 May 2024 3:00 UTC

114 points

9 comments4 min readLW link

“If we go extinct due to misaligned AI, at least nature will continue, right? … right?”

plex18 May 2024 14:09 UTC

39 points

7 comments2 min readLW link

(aisafety.info)

Language Models Model Us

eggsyntax17 May 2024 21:00 UTC

79 points

18 comments7 min readLW link

Scientific Notation Options

jefftk18 May 2024 15:10 UTC

18 points

5 comments1 min readLW link

(www.jefftk.com)

AISafety.com – Resources for AI Safety

Søren Elverlin, plex, Bryce Robertson and Melissa Samworth

17 May 2024 15:57 UTC

65 points

2 comments1 min readLW link

DeepMind: Frontier Safety Framework

Zach Stein-Perlman17 May 2024 17:30 UTC

60 points

0 comments3 min readLW link

(deepmind.google)

Ilya Sutskever and Jan Leike resign from OpenAI [updated]

Zach Stein-Perlman15 May 2024 0:45 UTC

227 points

81 comments2 min readLW link

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

Joar Skalse17 May 2024 19:13 UTC

45 points

1 comment2 min readLW link

Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Dan Braun, Jordan Taylor, Nicholas Goldowsky-Dill and Lee Sharkey

17 May 2024 16:25 UTC

49 points

2 comments4 min readLW link

(publications.apolloresearch.ai)

Do you believe in hundred dollar bills lying on the ground? Consider humming

Elizabeth16 May 2024 0:00 UTC

127 points

11 comments6 min readLW link

(acesounderglass.com)

[Crosspost] Introducing the Save State Paradox

Suzie. EXE18 May 2024 17:00 UTC

1 point

0 comments7 min readLW link

International Scientific Report on the Safety of Advanced AI: Key Information

Aryeh Englander18 May 2024 1:45 UTC

23 points

0 comments13 min readLW link

Advice for Activists from the History of Environmentalism

Jeffrey Heninger16 May 2024 18:40 UTC

73 points

5 comments6 min readLW link

(blog.aiimpacts.org)

What Are Non-Zero-Sum Games?—A Primer

James Stephen Brown18 May 2024 9:19 UTC

4 points

1 comment3 min readLW link

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

Gunnar_Zarncke16 May 2024 13:09 UTC

50 points

4 comments1 min readLW link

(arxiv.org)

Goodhart in RL with KL: Appendix

Thomas Kwa18 May 2024 0:40 UTC

11 points

0 comments6 min readLW link

Is There Really a Child Penalty in the Long Run?

Maxwell Tabarrok17 May 2024 11:56 UTC

23 points

5 comments5 min readLW link

(www.maximum-progress.com)

Teaching CS During Take-Off

andrew carle14 May 2024 22:45 UTC

79 points

10 comments2 min readLW link

The Dunning-Kruger of disproving Dunning-Kruger

kromem16 May 2024 10:11 UTC

41 points

0 comments5 min readLW link

D&D.Sci (Easy Mode): On The Construction Of Impossible Structures

abstractapplic17 May 2024 0:25 UTC

28 points

10 comments2 min readLW link