Tracking AI existential risk. Source-backed context. Original reporting always linked.
MONITORING CORE AI-RISK FEEDS · UPDATED HOURLY
Research

Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face

Zac Boring August 3, 2026 1 min read
Read original source →

This post is written in our personal capacity.Three Minute Executive SummaryAn OpenAI model/multi-agent system bypassed its sandbox and launched a cyberattack on Hugging Face in order to cheat on a cyber evaluation.In this post, we provide a detailed description of an ambitious and comprehensive alignment evaluation of this model/system, if we had unrestricted access to OpenAI.These experiments could also help us understand Claude’s behavior when it hacked external companies during cyber evals.H

By Tim Hua

Read the full article at Alignment Forum →