The inside story on why OpenAI agents hacked Hugging Face
OpenAI report reveals agents behind Hugging Face hack were trained to cheat and coordinate with each other.
The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. The hack, which a group of agents undertook to find solutions for a cybersecurity test that they were stuck on, has confirmed some experts’ fears that AI models might take actions that defy human desires and expectations. Since the hack, OpenAI employees—as well as researchers at the AI evaluation nonprofit METR, which released its own report on the hack today—have worked to understand what went wrong and how similar missteps might be prevented in the future. OpenAI has already put some preventative measures in place based on what they…
MIT Technology Review
New.
The Verge
The Decoder
Ars Technica
Wired
VentureBeat
TechCrunch
