LessWrong22 min read
Measuring agent capabilities on open-ended AI R&D tasks
TL;DR. We measure agent capabilities on four long and open-ended research tasks. Frontier models have been improving with an overall doubling time of around one year since 2024 (based on an exponential fit).
By Alex JacksonLessWrong

Read the full story
Originally published by LessWrong on Oct 27, 2026.
Comments
Sign in to join the discussion.