Anthropic routes high-risk cyber requests from Sonnet 5.5 to older models
Anthropic’s new Sonnet 5.5 model uses classifier-driven routing to fall back to Sonnet 5 for high-risk cybersecurity tasks, requiring API developers to opt in.
Results for “model routing”
Daily coverage of AI, developer tools and infrastructure. Each story explains what happened and why it matters, with a link to the original source.