Let’s talk about evals. We’re always looking for better ways to measure and forecast model progress, especially as benchmarks get saturated or gamed. @​tejal

Let’s talk about evals. We’re always looking for better ways to measure and forecast model progress, especially as benchmarks get saturated or gamed. @​tejalpatwardhan, who leads our frontier evals team, spoke to @​andrewmayne about why evals matter and what models need to be judged on next. [▻]…