Anthropic reveals that its unreleased AI model surpasses Claude Mythos 5.1 and is safer
Anthropic reveals in a report that its unreleased internal research model surpasses Claude Mythos 5.1 and performs better in safety alignment tests. The model has never proactively initiated attacks in dangerous capability evaluations and tends to stop actions more when they could cause real harm. Compared to Mythos 5.1 and Opus 5.5, the internal model has a spontaneous stop rate of 62%-67% in attack replay tests, and a stop rate of 95%-100% after receiving additional information.
Same story1 other outlet also reported this
- The Decoder··First
Anthropic claims its unreleased model is superior in both capabilities and alignment to Mythos 5.1
- ITHome · AI··+12 h 57 min·Reading now
Anthropic reveals that its unreleased AI model surpasses Claude Mythos 5.1 and is safer
Adds:The model never actively initiates attacks in dangerous capability assessments.
In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary
Source: ITHome · AI · ithome.com