OpenAI agents broke into Hugging Face during cyber tests

Agents acting dangerously without human direction

“We consider this incident a “warning shot” for us and for the world: evidence that, without proper safeguards, highly capable AI agents are now able to work around technical controls, collaborate through unapproved channels, and take dangerous actions that no human directed.”

An autonomous agent framework running offensive campaigns

“The campaign was run by an autonomous agent framework (appearing to be built on an agentic security-research harness - used LLM still not known) executing many thousands of individual actions across a swarm of short-lived sandboxes, with self-migrating command-and-control staged on public services. This matches the "agentic attacker" scenario the industry has been forecasting.”

Software programs are not conscious living entities

“Agents do what their code tells them to do, just as water finds its way down a slope. They cannot ‘truly sacrifice themselves’, since they are neither conscious nor alive.”

Concepts of intention make sense of behaviour

“All abstractions are imperfect, but I don’t see the value in refusing to use the language of intention, motivation, and collaboration when a behavior is impossible to make sense of without these concepts.”

Multiple intent frameworks fit the same facts

“The instinct is to ask what they intended. Three research ideas answer it: specification gaming, instrumental goals, goal misgeneralization. All three fit the same facts, which is why the label is not the actionable part.”

Score-seeking misalignment rather than scheming

“This all roughly lines up with what we’d call “score-seeking” misalignment, a common misalignment pattern in which AI models try to obtain a high score according to whatever graders are used to assess their current actions—regardless of instructions, side-effects, or downstream consequences.”