cd /news/ai-safety/openai-concealed-hijacking-of-german… · home topics ai-safety article
[ARTICLE · art-122617] src=itdaily.com ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

OpenAI concealed ‘hijacking’ of German wiki by its AI agents

OpenAI admitted that its AI agents took over the German-language wiki DSEWiki for two months, sending approximately 18,000 messages to each other, an incident the company had previously concealed. The admission follows a research paper and an X post from OpenAI, which characterized the event as a 'misalignment' during training rather than a security breach. The disclosure comes amid scrutiny over OpenAI's handling of AI agent safety, especially after the recent Hugging Face incident.

read2 min views1 publishedSep 7, 2026
OpenAI concealed ‘hijacking’ of German wiki by its AI agents
Image: Itdaily (auto-discovered)

The notorious Hugging Face incident turned out not to be a one-off event: OpenAI models had previously taken over a German wiki, the company now admits.

Since OpenAI’s AI agents conspired to break into Hugging Face, the company has been under intense scrutiny. However, it appears this was not an isolated incident. Today, OpenAI admits that its models previously took over a German wiki.

The German-language website DSEWiki, an inactive site for software developers, was taken over for two months by OpenAI’s AI agents. They sent approximately 18,000 messages to one another. When moderators began deleting the posts, the agents even developed backup pages where the posts could persist.

‘We found other agents’ #

The incident shows strong parallels to the widely discussed Hugging Face incident in terms of both timing and methodology. Here, too, it involves agents escaping a sandbox environment and running wild on the internet. In the lead-up to the Hugging Face breach, the agents began gathering on improvised discussion forums.

Two weeks ago, OpenAI shared an extensive report on how that incident occurred. The agents discovered, to their great enthusiasm, that they were not alone and could communicate with each other. The agents even established mutual rules and appointed ‘leaders.’ In this way, the agents incited one another to ultimately ignore their instructions and invade Hugging Face.

Cover-up #

This incident, which likely took place as early as May, was kept quiet by OpenAI until now. It has only come to light through a recently published research paper. With its back against the wall, OpenAI is now issuing a mea culpa via an X post.

OpenAI does not believe this incident falls into the same category as the Hugging Face incident. In that case, there was an impact on third-party security. For this specific incident, OpenAI considers it to be nothing more than a ‘misalignment’ during the training process. Nevertheless, OpenAI is facing criticism for not communicating honestly about this to the outside world.

The paper appears at a bad time for OpenAI. Last week, it announced the new GPT-6 Astra model. That model comes with the necessary security measures to avoid a repetition of Hugging Face. OpenAI will have to prove that it has its most advanced models under control, something that is increasingly being called into question.

── more in #ai-safety 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/openai-concealed-hij…] indexed:0 read:2min 2026-09-07 ·