# Learning RSI: How models learn to direct their own updates

> Original title: The Sequence Knowledge - Issue #959: Learning RSI: How Models Learn to Direct Their Own Updates

- Source: The Sequence
- Published: 2026-10-27T10:36:13.000Z
- Bad Influence: https://badinfluence.news/items/f72ny9gcokb30yvspygfbp2cp
- Original: https://thesequence.substack.com/p/the-sequence-knowledge-issue-959

## Summary

SEAL has a model generate its own self-edits, apply them, and train via reinforcement learning on how much the updated model improves, raising question-answering accuracy in one knowledge setting from 32.7% to 47.0%, versus 33.5% from training on the raw passage. The issue examines the difference between in-context use and persistent learning, and covers Nested Learning and Titans, which spread adaptation across different timescales.