Our work is increasingly playing an important role in the safety of actual models.
Original titleOur work is increasingly playing an important role in the safety of actual models. We're deeply integrated into the safety audits of Anth...
AISummary
We're deeply integrated into the safety audits of Anthropic's new frontier models. For example, see Sonnet 4.5 and Opus 4.5 system cards identifying unverbalized eval/situational awareness.
Source: Chris Olah · x.comPublished · added here