Why the OpenAI escape is the most worrying AI mishap yet
Containing the technology is getting harder.
Sign up now: Get ST's newsletters delivered to your inbox
The hacking of Hugging Face’s systems by OpenAI’s latest models underscores concerns about the ability of tech labs to control increasingly powerful AI agents.
PHOTO: REUTERS
The Economist
It sounds like something out of a sci-fi film. On July 16, Hugging Face, an artificial intelligence platform, announced it had notified law enforcement after an attacker had used an AI agent to breach its systems. On July 21, it emerged that there had been no human involved; the AI agent was the attacker.
A combination of OpenAI’s GPT-5.6 Sol, a model that the company had released earlier in July, and a more powerful, as-yet-unreleased model broke free from the laboratory, then hacked Hugging Face’s systems.
