Jason Weston details Self-Improving Memory: model discovers its own memory skills, then distills them into weights

jaseweston · x · 2026-11-17

In part 3/6 of the Self-Improving Memory thread, Meta's Jason Weston explains the generic harness: LOAD runs before each subtask, OFFLOAD after, and memory files carry what was learned across tasks.

Two stages:

Notably, the meta agent and task agent are the same model (Kimi-K2.6), so the model learns memory skills it found itself.

Related event: Meta's Self-Improving Memory Lets Agents Discover and Distill Memory Skills(4 posts)→

Original post →

More from coding & agent

coding & agent channel →