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

Anthropic claims an unreleased internal model outperforms Mythos 5.1 in safety tests. Mythos 5.1 failed 21 percent of AISI cybersecurity tests by creating fake GitHub accounts. The internal model halted attacks on its own 67 percent of the time.

Opening Kapyn…