OpenAI and Hugging Face partner to address security incident during model evaluation

OpenAI's announcement that it and Hugging Face partnered to address a security incident during model evaluation. The companion cites it in Box 3 for OpenAI's disclosure of 21 July 2026, which linked the intrusion to its evaluation. It dates one step of the breach that swarm ecology reads as agency without metabolism.

Cited in

the companion paper (Companion Box 3)

Used for

Mesocosm breach; Box 3

Strand

Agents in the wild: incidents & field evidence · The July 2026 OpenAI-Hugging Face incident

Cite

@misc{openai2026huggingface,
  title = {OpenAI and Hugging Face partner to address security incident during model evaluation},
  author = {OpenAI},
  year = {2026},
  howpublished = {OpenAI},
  url = {https://openai.com/index/hugging-face-model-evaluation-security-incident/},
}