Cooperative AI

TagLast edit: 31 May 2023 3:13 UTC by Eevee🔹

Cooperative AI is a subfield of artificial intelligence that aims to improve the ability of AI systems to engender cooperation between humans, machines, and institutions. It can therefore also be seen as part of the AI safety landscape, aimed at preventing AI risks and existential risks resulting from cooperation failure.

Further Reading

Baumann, Tobias (2022) Cooperative artificial intelligence, arXiv:2202.09859.

Dafoe, Allan et al. (2020) Open problems in cooperative AI, arXiv:2012.08630.

Dafoe, Allan et al. (2021) Cooperative AI: machines must learn to find common ground, Nature, vol. 593, pp. 33–36.

Related Entries

AI safety | Center on Long-Term Risk | Cooperative AI Foundation

Cooperative AI: Three things that confused me as a beginner (and my current understanding)

C Tilli16 Apr 2024 7:06 UTC

56 points

10 comments6 min readEA link

[Question] Game theory work on AI alignment with diverse AI systems, human individuals, & human groups?

Geoffrey Miller2 Mar 2023 16:50 UTC

22 points

2 comments1 min readEA link

Project ideas: Backup plans & Cooperative AI

Lukas Finnveden4 Jan 2024 7:26 UTC

25 points

2 comments13 min readEA link

(lukasfinnveden.substack.com)

Brian Tomasik on cooperation and peace

Vasco Grilo🔸20 May 2024 17:01 UTC

27 points

1 comment4 min readEA link

(reducing-suffering.org)

AGI Battle Royale: Why “slow takeover” scenarios devolve into a chaotic multi-AGI fight to the death

titotal22 Sep 2022 15:00 UTC

49 points

11 comments15 min readEA link

Boomerang—protocol to dissolve some commitment races

Filip Sondej30 May 2023 16:24 UTC

20 points

0 comments8 min readEA link

(www.lesswrong.com)

[Job] Managing Director at the Cooperative AI Foundation ($5000 Referral Bonus)

Lewis Hammond3 Jul 2023 16:02 UTC

31 points

0 comments1 min readEA link

Launching Foresight Institute’s AI Grant for Underexplored Approaches to AI Safety – Apply for Funding!

elteerkers17 Aug 2023 7:27 UTC

48 points

0 comments2 min readEA link

2024 S-risk Intro Fellowship

Center on Long-Term Risk12 Oct 2023 19:14 UTC

89 points

2 comments1 min readEA link

Center on Long-Term Risk: Annual review and fundraiser 2023

Center on Long-Term Risk13 Dec 2023 16:42 UTC

78 points

3 comments4 min readEA link

CLR Summer Research Fellowship 2024

Center on Long-Term Risk15 Feb 2024 18:26 UTC

89 points

2 comments8 min readEA link

Apply to the Cooperative AI PhD Fellowship by October 14th!

Lewis Hammond5 Oct 2024 12:41 UTC

35 points

0 comments1 min readEA link

Apply to the Cooperative AI Summer School!

reddington3 Apr 2024 12:13 UTC

26 points

0 comments1 min readEA link

GovAI Annual Report 2021

GovAI5 Jan 2022 16:57 UTC

52 points

2 comments9 min readEA link

Announcing the CLR Foundations Course and CLR S-Risk Seminars

James Faville19 Nov 2024 1:18 UTC

32 points

0 comments3 min readEA link

Lewis Hammond: Introduction to Cooperative AI

Group Organizer29 Apr 2022 9:52 UTC

3 points

0 comments1 min readEA link

Refer the Cooperative AI Foundation’s New COO, Receive $5000

Lewis Hammond16 Jun 2022 13:27 UTC

42 points

0 comments3 min readEA link

Open Problems in AI X-Risk [PAIS #5]

TW12310 Jun 2022 2:22 UTC

44 points

1 comment36 min readEA link

Stackelberg Games and Cooperative Commitment: My Thoughts and Reflections on a 2-Month Research Project

Ben Bucknall13 Dec 2021 10:49 UTC

18 points

1 comment9 min readEA link

No comments.