LoRA Creator Edward Hu Publishes Guide on Post-Training Open-Source Models with RL

iamrobotbear · x · 2026-09-05

Edward Hu, the creator of LoRA fine-tuning, has published a blog post on how to post-train open-source models, drawing strong recommendations from practitioners including Instacart CEO Brendan Foody.

Those sharing it call it a must-read — reportedly one of the best open-source writeups on actually running RL training for knowledge-work agents at scale.

For anyone post-training open models, first-hand guidance from the technique's original author makes this especially worth reading.

Original post →

More from coding & agent

coding & agent channel →