Trajectory(@trajectorylabs):It's time to rethink RL. Translating real world use into model improvements requires redesigning post-training algorithms for non-verifiable, per token rewards. At @aiDotEngineer 's World Fair, we share our insights into scaling algorithms like SDPO for continual learning.

Trajectory

@trajectorylabs

Building the platform for Continual Learning

加入 December 2025

1 正在关注 4.9K 粉丝

Trajectory@trajectorylabs

2026.08.17 16:11

It's time to rethink RL. Translating real world use into model improvements requires redesigning post-training algorithms for non-verifiable, per token rewards. At @aiDotEngineer 's World Fair, we share our insights into scaling algorithms like SDPO for continual learning.

显示更多