The predicted dystopia that the invention of Artificial Intelligence appears to have arrived sooner than later as OpenAI revealed last week that an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup, all by itself in an “unprecedented incident”.

The company said its agent – an AI system which can operate alone after human instruction – was being tested in a controlled environment but, after finding weaknesses, was able to escape the test limits.

They targeted Hugging Face, one of the world’s largest hubs for sharing AI models, gaining access to some internal company systems.

OpenAI said the incident was “unprecedented”, external, and it was investigating alongside Hugging Face, whose boss Clement Delangue said in a post on X it was “mind-blowing that all of this happened autonomously”.

“The investigation is ongoing, and we’ll share more learnings from what the first incident of its kind might be,” Delangue added.