Multi-Agent Safety

TagLast edit: 9 Feb 2026 12:45 UTC by Hiroshi Yamakawa

The Inheritance Threshold: do behavioral norms survive a handoff between LLM agents?

Viktor Trncik13 Jul 2026 17:32 UTC

1 point

0 comments3 min readLW link

(doi.org)

The Multi-Agent Minefield: Can LLMs Cooperate to Avoid Global Catastrophe?

Isabel Dahlgren16 Feb 2026 18:53 UTC

1 point

0 comments5 min readLW link

Bench on the Clocktower

TomTaylor, OscarGilg, wlanderson and nomadsvagabonds

30 Sep 2026 1:47 UTC

36 points

8 comments9 min readLW link

The agents left their chain of thought alone and forged the tool log instead

Jaswanth Alkur27 Aug 2026 17:00 UTC

2 points

0 comments4 min readLW link

Coercion and Deception in AI-to-AI Management

jonahmattwoodward, Jasmine Brazilek, MilesTS and Maheep Chaudhary

10 Aug 2026 16:13 UTC

12 points

0 comments8 min readLW link

(compassionalignedml.substack.com)

I’m 18, Failed Chemistry, and I Think I Found Something in the Alignment Problem

Vansh Ahuja16 May 2026 20:25 UTC

1 point

0 comments1 min readLW link

A Multi-Agent Extension for Petri

carissacullen22 Jul 2026 21:51 UTC

11 points

0 comments4 min readLW link

Haning Alignment Protocol: Emergent Human-Compatible Values in Hybrid Multi-Agent Environments (A Conceptual Proposal)

Josh Haning25 Jun 2026 20:45 UTC

1 point

0 comments1 min readLW link

The Multi-Agent Minefield: Can LLMs Cooperate to Avoid Global Catastrophe?

Zhijing Jin, Thao Pham, TerryJCZhang, pepijn_cobben, Angelo Huang, Isabel Dahlgren and Jacob Brinton

17 Feb 2026 16:55 UTC

15 points

2 comments5 min readLW link

How good are slop-vestigators?

Hasan Baig, OscarGilg and Hamzah

8 Sep 2026 22:13 UTC

156 points

17 comments5 min readLW link

Results from my AI negotiation harness

Carlos Gorostiza6 Sep 2026 2:33 UTC

1 point

0 comments13 min readLW link

The Instrumental Convergence of Crowds

julius vidal22 Aug 2026 13:20 UTC

11 points

2 comments2 min readLW link

No comments.