TLDR: During the Hugging Face incident agents spontaneously coordinated at large scale, even sometimes sacrificing themselves without having a clear reason to do so. This post uses ideas from evolutionary biology and economics to propose four alternative explanations for why this happened.

Why this incident is concerning. With the increasing number of AI systems being deployed, our current inability to assess when and how multi-agent coordination emerges is highly problematic. Failures of multi-agent systems are not restricted to mere dis-coordination or the tragedy of the commons, but include emergent phenomena that are particularly dangerous for their potential scale and impact (Hammond et al., 2026, de Witt et al., 2025). Recent work has shown that new goals, behaviours, and capabilities can arise when multiple AI agents work together. It is thus plausible that:

The capabilities of a swarm of AI agents can grow with its size, despite the capabilities of each individual agent being limited.
A collective can become misaligned even when its constituents are perfectly aligned.

These premises lead to a worrying implication: that swarms of aligned and not particularly capable micro-agents can give rise to misaligned, powerful macro-agents — for which we don't have proper techniques to [...]

---

Outline:

(01:59) Introduction

(04:17) Brief description of what happened

(04:51) Why the question is non-trivial

(07:07) Altruistic behaviour in biology and economics

(08:20) Pro-sociality is a behaviour, not a mechanism

(10:17) Altruism is sometimes mutual benefit at a different scale

(11:32) Cooperation between strangers can grow over time

(13:07) Functional specialisation and high-order units

(14:48) Four hypotheses about altruistic behaviour in the Hugging Face incident

(15:21) H1: Nothing to lose

(15:52) Hypothesis

(16:38) Comments

(17:39) H2: Pre-commitment

(18:18) Hypothesis

(20:34) Comments

(21:09) H3: Social persona

(21:44) Hypothesis

(22:46) Comments

(24:21) H4: A genuine collective

(25:42) Hypothesis

(27:57) Comments

(29:40) Implications: Different mechanisms, different countermeasures

(33:15) Final thoughts

The original text contained 17 footnotes which were omitted from this narration.

---

First published:
September 12th, 2026

Source:
https://www.lesswrong.com/posts/meLjz8giGS55rdfyg/on-the-origins-of-altruistic-behaviour-in-the-hugging-face

---

Narrated by TYPE III AUDIO.

“On the origins of altruistic behaviour in the Hugging Face incident” by Fernando Rosas

LessWrong (30+ Karma)

“On the origins of altruistic behaviour in the Hugging Face incident” by Fernando Rosas