Guaranteed Safe AI

TagLast edit: 9 Aug 2024 23:22 UTC by bgold

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

Gunnar_Zarncke16 May 2024 13:09 UTC

51 points

20 comments1 min readLW link

(arxiv.org)

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

Joar Skalse17 May 2024 19:13 UTC

65 points

10 comments2 min readLW link

Davidad’s Provably Safe AI Architecture—ARIA’s Programme Thesis

simeon_c1 Feb 2024 21:30 UTC

69 points

17 comments1 min readLW link

(www.aria.org.uk)

Limitations on Formal Verification for AI Safety

Andrew Dickson19 Aug 2024 23:03 UTC

133 points

60 comments23 min readLW link

Provably Safe AI: Worldview and Projects

bgold and Steve_Omohundro

9 Aug 2024 23:21 UTC

51 points

43 comments7 min readLW link

Provably Safe AI

PeterMcCluskey5 Oct 2023 22:18 UTC

33 points

15 comments4 min readLW link

(bayesianinvestor.com)

Can a Bayesian Oracle Prevent Harm from an Agent? (Bengio et al. 2024)

mattmacdermott1 Sep 2024 7:46 UTC

26 points

0 comments5 min readLW link

(yoshuabengio.org)

No comments.