Using Agents to Fine-Tune Custom Models

pritisinghhhh · x · 2026-07-17

The post introduces an agent named RL Tutor, designed to help the author **post-train their own models**. - This week, thinkymachines released **inkling**, an open-weights model customizable and fine-tunable via the **tinker API**. - The author notes a long-standing desire to learn how to fine-tune models independently, prompting the creation of this agent to assist with the process. - The emphasis isn't merely on the ability to fine-tune, but on delegating both the learning and execution of the fine-tuning process to a dedicated agent.

Original post →

More from coding & agent

coding & agent channel →