Swarmchasers" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark
- Anthropic: 66 events in the last 90 days
- Previous: earlier the same day · ‘Gambling with our lives’: former Anthropic researcher quits in alarm at what he saw in 3 years of working at the lab
What happened
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 reasonin…
Summary assembled by rule from the sources below