How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Using GRPO to Beat o1, o3-mini, and R1 on Temporal Clue

calendar_today March 6, 2025 person Brad Hilton and Kyle Corbitt domain openpipe

How we used GRPO to surpass R1, o1, o3-mini on a reasoning-heavy game called “temporal clue”

open_in_new Read original post