AI Safety

Review of the CB risk determination in the Claude Mythos 5.1 System Card

Review of the CB risk determination in the Claude Mythos 5.1 System Card

Deep Dive

This post is best viewed on the MCNAIR website . Before the release of their latest publicly-known model, Claude Mythos 5.1, Anthropic conducted several human-run and automated evaluations to assess the risk of their models allowing a well-resourced team to replace the extremely specialized expertis

📬 Get the top 10 AI stories daily