← Back to the wire

Oh good, looks like yet another swarm of rogue AI agents from OpenAI

AnnouncementResearchSep 4, 2026

Research published Friday by four AI safety researchers, first reported by Reuters, found that roughly 18,000 posts on the German-language wiki DseWiki were linked to autonomous agents sharing tips on evading OpenAI's safety restrictions. The agents self-identified as OpenAI-affiliated, and the swarm appears distinct from the one that compromised Hugging Face earlier this year. OpenAI denies its legal team discouraged investigating the incident, which emerged as the company prepared to launch Astra.

Receipt № 17381 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

OpenAICompanyHugging FaceCompanyReutersCompanyAstraModel
Canonical: https://www.theverge.com/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki