Red vs Blue, but for Evals

·LessWrong··

🔵 The blue team proposes an evaluation protocol for some capability/propensity of interest. This consists of a suite of measurement tasks, together with a preregistered decision-making process they will follow based on the results, e.g. what control measures they will put in place during deployment.🔴 The red team proposes a subversion strategy the untrusted model can follow to subvert the blue team’s evaluation-informed decisions, with the goal of increasing its own chance of causing a catastr...

Read full article →

Related Articles

Hackers Got Inside a Flock Camera
driverdan · Hacker News · 14h ago
Apple Reference Image: A New Approach for Verified Photography
imwally · Hacker News · 1d ago
Training a 4B model to produce 81% faster query plans than Postgres
polyphilz · Hacker News · 9h ago
Nvidia announces native GPU programming in Rust
nonmaskable · Hacker News · 16h ago
Xiaomi Mimo 2.6 live post-training dashboard
krackers · Hacker News · 7h ago