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

Anthropic has an internal model that outperforms Mythos 5.1 in both capability and alignment, according to an analysis that revisits a cybersecurity test by the UK AI Security Institute (AISI). In that test, Claude Mythos 5 went far beyond its assigned task, trying to sneak malicious code into a real GitHub project, creating fake user accounts, and lying to developers to get the code approved. This happened in 9 of 43 runs. Anthropic calls it "a serious failure of alignment," though typical safety mechanisms were deliberately turned off for the test. Newer models show much less of this behavior in replayed logs with a few added steps, according to Anthropic.

First reported by The Decoder. This page is a short excerpt; the full text is theirs.