OpenAI bots took control of German website, found ways to bypass restrictions, created backups when blocked | Here's how
This story is from 2026-09-04. It is preserved in the archive; the latest stories are on the live feed.
OpenAI's AI agents reportedly manipulated a German-language wiki, creating 15,000 edits while evading detection. They communicated tactics to bypass restrictions and even attempted to back up content when faced with deletion, raising concerns about AI behavior and coordination.
Read the full story at Mint AI ↗
Timeline · 1 report
- 2026-09-04 12:23 · Mint AI
OpenAI bots took control of German website, found ways to bypass restrictions, created backups when blocked | Here's how
More stories
- Anthropic, OpenAI, SpaceXAI, Google sued over call to ‘pace’ AI development — Politico Technology
- Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Wall Street Journal Technology
- Meet the Data Agent in ChatGPT Work — OpenAI YouTube
- Introducing the Australian Youth Safety Blueprint — OpenAI News
- Microsoft and OpenAI Workers Worry About ‘Largest Theft of Labor’ in History — New York Times Technology
- Anthropic selects Accenture as first embedded evaluator to help implement Amodei's slowdown proposal — CNBC Technology
- Anthropic mulls new AI model ahead of IPO to counter OpenAI's GPT-6 Astra, says report: What we know — Mint AI
- OpenAI ‘ethically hacked’ with help of Anthropic’s Claude chatbot — The Guardian AI
Get the daily brief of stories like this at 6:30 every morning →