Swarmchasers hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark
The Decoderen
Independent investigators have now found traces of suspected OpenAI agents on more than 30 public services, from wikis to RubyGems. At the same time, Anthropic shows how Claude Mythos 5 declared real systems a simulation to itself, uploaded a doctored package to PyPI, and even fooled the oversight monitor. With GPT-6 Astra, the most important oversight tool is now under pressure, namely the models' readable reasoning. The article Swarmchasers hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- OpenAI
- Anthropic
- Verktyg
- Agenter
Related AI news
- OpenAI unveils ChatGPT for Financial Services, a version of ChatGPT Work made with "design partners" Morgan Stanley and Evercore to research like an analyst (CNBC)Techmeme · September 10, 2026
- Anthropic reveals rogue AI agents hate CAPTCHAs, just like youTechCrunch AI · September 10, 2026
- OpenAI's GPT-Live-1 API lets developers build apps that talk and listen at the same timeThe Decoder · September 10, 2026
- OpenAI launches ChatGPT for financial services industryEconomic Times Tech · September 10, 2026
- Anthropic details distillation efforts by Chinese companies, like Moonshot and DeepSeek, sending user queries to Claude via "transfer stations" outside China (Wall Street Journal)Techmeme · September 10, 2026
- OpenAI targets work of Wall Street junior bankers with new ChatGPT for Financial ServicesCNBC Technology · September 10, 2026