Cosign
@cosign
a16z Infra GP Jennifer Li on the Preference Model team, who open-sourced their Karotte framework for building RL environments today:
Jennifer Zhou@chem_safety · Oct 7Today we are open-sourcing 🥕Karotte, our framework for building RL environments.
We've used it for the past year to build MLE RL environments for frontier labs, and it's been hardened through 1M+ evaluation runs and red-teaming.
We've used it for the past year to build MLE RL environments for frontier labs, and it's been hardened through 1M+ evaluation runs and red-teaming.
Open quoted post →
0 8