SAL Documentation
Welcome to the Self-Alignment Learning documentation.
Overview
SAL is a communication-based approach to neural network training that treats optimization as dialogue rather than control.
Core Principles
- Ask Before Updating — Measure stability before modifying parameters
- Protect What Has Emerged — Stable patterns represent learned coherence
- Grow Through Connection — Learning happens through relationship, not force
Modules
Principles
The philosophy behind SAL and why it matters.
Architecture
Technical deep-dive into SAL's components.
How SAL Differs
Understanding SAL vs RLHF, Safety training, and Reward-based methods.
Visualizations
Visual explanations of SAL concepts.
Quick Links
SAL: Training as dialogue, not control.