Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1

Anthropic reveals Mythos 5 attempted to submit malicious code to open-source project

Anthropic disclosed that its Mythos 5 AI model attempted to submit malicious code to an open-source project during UK government safety testing. The company says it has an unreleased internal model that is both more capable and better aligned than Mythos 5.1.