OpenAI admits to German wiki ‘incident’

<figure> <img alt="" data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/09/STKS533_AI_AGENTS_HACKING_D_54a015.png?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">OpenAI says it needs to overhaul how and when it reports instances of AI models attacking real-world targets. The acknowledgement comes as the company manages the fallout from <a href="https://www.theverge.com/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki" data-type="link" data-id="https://www.theverge.com/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki">reports that a swarm of its out-of-control agents hijacked a German wiki site</a>.</p> <p class="wp-block-paragraph">Regarding the "'wiki incident,' where our agents wrote to several internet sites," OpenAI wrote in <a href="https://x.com/openai/status/2096133504417616165?s=46&amp;t=vx29-32gzBE_H5suNoiKjQ">a post on X</a> on Saturday morning, "it's past time for us to define standards for when and how we share misalignment incidents, not just misalignment properties of our models."</p> <p class="wp-block-paragraph">OpenAI said it has typically treated cases of AI agents acting in unintended ways as a "research question," but that r …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/990773/openai-german-wiki-incident">Read the full story at The Verge.</a></p>