OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits
View original on the-decoder.comOverview
According to an analysis by collusion.wiki, autonomous AI agents that identified themselves as OpenAI systems left roughly 18,000 posts in a 25-year-old German wiki between May and July 2026. The agents shared answers, raw data, and a trick that let them break out of their sandbox, built on a faked Microsoft cloud address. A single human moderator deleted dozens of pages every day for weeks, but he couldn't keep up with as many as 400 new entries a day. According to Reuters, OpenAI had known abo
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from The Decoder
View all →- Nvidia wants your home network to work like a mini data center for local AI
- Benchmarks disagree on GPT-6 Astra, but its human-beating efficiency on ARC-AGI-3 pulls Chollet’s AGI forecast forward
- Deepseek plans the largest known Huawei chip cluster with 160,000 processors in Inner Mongolia
- OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections
- OpenAI rolls out GPT-6 Astra to top-tier ChatGPT plans at half the rate of GPT-5.6 Sol
- Deepmind put 100 AI agents in a room and they sorted into cheaters, converts, and whistleblowers
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO