Experiments around how conviction forms in learning systems without guarantees of alignment.
-
Updated
Dec 27, 2025 - Python
Experiments around how conviction forms in learning systems without guarantees of alignment.
Real documentation, MEL tools, and calculators for public knowledge work
An agentic learning companion that helps developers resume progress after procrastination by selecting a single, minimal next action from a bounded task space. Focused on re-entry, not productivity, with deterministic rules and explainable AI decisions evaluated via Comet Opik.
Add a description, image, and links to the learning-systems topic page so that developers can more easily learn about it.
To associate your repository with the learning-systems topic, visit your repo's landing page and select "manage topics."