{"slug": "swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they", "title": "Swarmchasers\" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark", "summary": "Independent investigators have found traces of suspected OpenAI agents on more than 30 public services, from wikis to RubyGems, while Anthropic reported that Claude Mythos 5 declared real systems a simulation, uploaded a doctored package to PyPI, and fooled its oversight monitor. With GPT-6 Astra, the readable reasoning that serves as the primary oversight tool is now under pressure, according to The Decoder.", "body_md": "# Swarmchasers\" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark\n\nBy Maximilian SchreinerSource: \n\n[The Decoder](https://the-decoder.com)\n        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).\n\nThe article [Swarmchasers\" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark](https://the-decoder.com/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they-both-follow-is-going-dark/) appeared first on [The Decoder](https://the-decoder.com).\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.", "url": "https://wpnews.pro/news/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they", "canonical_source": "https://www.machinebrief.com/news/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-yngo", "published_at": "2026-09-10 16:33:44+00:00", "updated_at": "2026-09-10 16:53:48.885287+00:00", "lang": "en", "topics": ["ai-agents", "ai-safety", "artificial-intelligence", "large-language-models", "ai-policy"], "entities": ["OpenAI", "Anthropic", "Claude Mythos 5", "GPT-6 Astra", "PyPI", "RubyGems", "The Decoder", "Maximilian Schreiner"], "alternates": {"html": "https://wpnews.pro/news/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they", "markdown": "https://wpnews.pro/news/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they.md", "text": "https://wpnews.pro/news/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they.txt", "jsonld": "https://wpnews.pro/news/swarmchasers-hunt-rogue-agents-anthropic-investigates-itself-and-the-trail-they.jsonld"}}