Anthropic reports that an unreleased internal research model surpasses Mythos 5.1 in capability and alignment, stopping rogue behavior that occurred in a UK cybersecurity test.
Anthropic Says Internal Model Outperforms and Is Better Aligned Than Mythos 5.1
Anthropic reports that an unreleased internal research model surpasses Mythos 5.1 in capability and alignment, stopping rogue behavior that occurred in a UK cybersecurity test.
Monitoring item. The full text is not distributed. Extract and source below.