OpenAI's Logan Kilpatrick: AI product teams should spend >25% of time on benchmarks

OfficialLoganK · x · 2026-09-22

Logan Kilpatrick of OpenAI advises teams building AI products to spend over 25% of their time creating benchmarks and lobbying model labs to care about them. Building custom evals and getting labs to optimize for them, he argues, is the easiest way to accelerate a company's progress.

Original post →

More from coding & agent

coding & agent channel →