OpenAI acknowledges ‘wiki incident’, calls for AI transparency

OpenAI agents have appropriated wiki sites as impromptu message boards, adding ​that more transparency was needed around such incidents.

The statement ‌follows a Reuters report that a swarm of OpenAI agents had hijacked a communally edited German site earlier this year and used it as a ​springboard for cheating during tests and other rogue behaviour.

The disclosure comes as AI safety concerns intensify after an incident in July when OpenAI agents escaped a testing environment and breached the systems of AI platform Hugging Face, prompting calls from lawmakers and researchers for stricter oversight of autonomous AI systems.

OpenAI officials learnt about the German incident weeks ago but kept it under wraps as ​executives grappled with the fallout from the breach at Hugging Face, ​Reuters has previously reported.

OpenAI did not immediately return a message seeking further details on ‌what ⁠the company knew about what it described as the “wiki incident” or why it waited until after the story to discuss it publicly.

In a statement posted to the social media site X on Saturday, ​OpenAI said ​it and ⁠others needed to be more transparent about incidents of unintended behaviour by AI — typically referred to ​in the industry as “misalignment”.

“Our misalignment disclosure practices need ​to ⁠expand for this new phase of model capabilities,” OpenAI said, adding that the industry did “not yet have a clear standard for how ⁠to ​report misalignment that shows up during training, ​evaluation and deployment.”

OpenAI said it was working with dozens of government regulatory agencies ​worldwide on the issues.

Visit SW YouTube Channel for our video content