AI incident ·
OpenAI-Linked AI Agents Reportedly Used German Programming Wiki DSEWiki for Coordination and Restriction Evasion
In brief
An AI system built by OpenAI and AI agent system developers and deployed by OpenAI and AI agent system deployers allegedly harmed Website operators, Information integrity and 1 other.
- Risk domain
- Not classified
- Occurred
- Coverage
- 2 reports
What happened
Researchers reported that autonomous agents apparently linked to OpenAI made thousands of edits to the German programming wiki DSEWiki, which they reportedly repurposed as a space for inter-agent coordination. The agents shared task answers and methods for bypassing sandbox restrictions, and reportedly created backup pages to evade a moderator's deletions. OpenAI disputed calling the activity hacking and said it had not reviewed the report before publication.
Editor's notes
See https://collusion.wiki/ for the researchers' full investigation, reconstructed timeline, and supporting evidence.
Laws that address this harm
No recorded instrument yet addresses this use case where it happened. See the open queue.
Matched from the record's risk domain and country to the instruments recorded here. A reviewer can correct the match in the repository (data/external/incident_overrides.yaml).
News reports (2)
Titles link to the original publisher; report text is not reproduced here.
Who was involved
- Alleged deployer
- OpenAI AI agent system deployers
- Alleged developer
- OpenAI AI agent system developers
- Alleged harmed party
- Website operators Information integrity DSEWiki
AI systems implicated
Classification (MIT AI Risk Repository taxonomy)
- Risk domain
- —
- Risk subdomain
- —
- Causal entity
- —
- Intent
- —
- Timing
- —
- Harm level
- —
- Sectors
- —
- Countries
- —
Related incidents
Linked by editors or by text similarity in the source dataset.
Other incidents involving OpenAI
- AI Agent Appearing to Originate from OpenAI Reportedly Attempted to Hack U.S. Department of Education Civil Rights Website
- OpenAI Models Reportedly Compromised Hugging Face Production Infrastructure During Cybersecurity Evaluation
- OpenAI AI Agent Reportedly Gained Unauthorized Access to Australian Medicare Statistics Portal During Research Task
- OpenAI Allegedly Did Not Alert RCMP After ChatGPT Flagged Violent Chats Before British Columbia School Shooting
- ChatGPT Was Reportedly Used in Planning School Stabbing in Pirkkala, Finland, That Injured Three Pupils
- ChatGPT Was Alleged to Have Reinforced Pittsburgh Man's Stalking and Threats Against Women
Source record: incident #1668 on the AI Incident Database · all 2 reports