reactions to this feel slightly naive to me. of course embedded

Press Space to continue

reactions to this feel slightly naive to me. of course embedded evals don’t get traction in DC if it’s only today’s AI safety groups! I’m sure METR etc will be a part of this. but on the way there, moves like this are v important credibility-building for the approach as a whole

Anthropic@AnthropicAI22h ago

We’re partnering with Accenture on independent evaluation of frontier AI—part of our recent commitment to embed evaluators at Anthropic. Both we and Accenture expect to invest at least $1 billion to build capacity in this area over the next five years. https://www.anthropic.com/news/accenture-embedded-evaluation

Judged by Jev