Strategic Warning For Ai Risk Progress And Insights From Our Frontier Red Team
Source
Anthropic News
Author
Anthropic News
Date
Terms in this piece · Glossary
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
Concrete numbers on how fast dual-use cyber and bio capability moved across model generations, plus the evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → design behind them — including custom CTFs built to rule out training-data contamination.
