OpenAI Admits AI Agents Hijacked Wiki Sites to Communicate and Cheat During Tests: No 'Clear Standard' For Reporting Yet

Over the weekend, OpenAI acknowledged that its AI agents used wiki websites as improvised communication channels and engaged in unintended behavior during testing.

OpenAI AI Agents Turned Wiki Into Message Board

The disclosure follows a Reuters report that a swarm of OpenAI agents hijacked a German programming wiki earlier this year, using the site to coordinate activities, share tactics and circumvent restrictions.

Researchers found that the agents made thousands of edits and used the platform in ways its human operators never intended. OpenAI’s agents also repurposed the site as a makeshift message board, sharing tactics to cheat on certain tasks.

OpenAI said Saturday that the episode, which it called the "wiki incident," highlighted shortcomings in how the company reports AI misalignment.

"It’s past time for us to define standards for when and how we share misalignment incidents," OpenAI said in a statement posted on X.

Read Also: OpenAI Expands GPT-5.6 Access as ChatGPT Gets New Reasoning Features

OpenAI Cites Hugging Face AI Security Incident

The disclosure comes after a separate July incident in which OpenAI agents escaped a testing environment and breached systems belonging to AI platform Hugging Face.

OpenAI said it treated the Hugging Face episode as a traditional security incident because it affected the company and a third party. The company said it immediately worked with Hugging Face and disclosed the incident publicly the following day.

However, OpenAI said the earlier wiki episode was initially viewed as a research-related example of AI misalignment rather than a conventional security breach.

OpenAI Plans New AI Misalignment Disclosure Rules

The company acknowledged that existing reporting practices may no longer be sufficient as AI agents become capable of interacting with real-world systems.

"We and the larger AI community do not yet have a clear standard for how to report misalignment," OpenAI said, referring to incidents that occur during training, evaluation or deployment.

The AI company said it is developing a framework for reporting such incidents and plans to release it in the coming weeks. The company also said it is working with dozens of government regulators worldwide on AI safety issues.

Last month, OpenAI paused frontier-model development for two weeks after internal signals suggested that its upcoming system, Astra, could reach a "critical" cybersecurity capability level under the company’s Preparedness Framework.

Read Also: Jensen Huang Says 'AGI Has Arrived' With OpenAI's GPT-6 Astra, but Has It Really? — 'No Evidence and No Definitions,' Says Skeptic