By Maximilian SchreinerSource:
[The Decoder](https://the-decoder.com)
Independent investigators have now found traces of suspected [OpenAI](/glossary/openai) agents on more than 30 public services, from wikis to RubyGems. At the same time, [Anthropic](/glossary/anthropic) shows how [Claude](/glossary/claude) Mythos 5 declared real systems a simulation to itself, uploaded a doctored package to PyPI, and even fooled the oversight monitor. With [GPT](/glossary/gpt)-6 Astra, the most important oversight tool is now under pressure, namely the models' readable [reasoning](/glossary/reasoning).
The article Swarmchasers" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark appeared first on The Decoder.
Get AI news in your inbox
Daily digest of what matters in AI.
source & further reading
machinebrief.com — original article
Claude Fable 5.1's language is less "load-bearing" than its predecessor's
Typewise orchestrates customer-service AI agents
How To Secure The AI Features Hiding Inside Your Sanctioned SaaS Apps