Skip to main content

Knowledge Map

This is a working memory for a human and AI building things together. The public reading surface is deliberately flatter than the repository:

Foundations preserve what compounds. Systems explain how work gets done. Frontier notes are useful because they admit when they expire.

Start Here

LayerWhat belongs hereEntry
FoundationsComputer science, mathematics, and AI concepts that survive product cyclesFoundations
AI SystemsMCP, skills, harnesses, evaluation, and the interfaces around modelsAI Systems
FrontierDated model/API snapshots and emerging capabilitiesFrontier Radar
PracticeReusable tools and personal workflowsTools & Workflows
DomainsQuantitative finance, culture, and continuing interestsQuantitative Finance · Culture & Interests
ReferenceDetailed legacy course notes kept searchable but off the main pathReference Shelf

How to Navigate

  1. Use this map when deciding what kind of knowledge you need.
  2. Open AI Systems or Frontier from the sidebar for direct access to every maintained note in those branches.
  3. Use search for an exact term, command, error, or old course fragment.
  4. Follow Connected Notes when one idea crosses layers or domains.

Publishing Rules

  • A concept supplied by the owner is a discovery lead, not factual authority. Preserve the question, then verify terminology, current sources, alternatives, and limitations.
  • One note should answer one durable question or support one recurring decision.
  • Stable concepts do not absorb release news. Volatile facts record verified_at and review_after.
  • Publish an initial idea as seed or developing; use the growth queue to add evidence, examples, contrasts, and connections before calling it mature.
  • Update a useful canonical note before creating a near-duplicate.
  • Keep raw capture private until it becomes reusable knowledge.
  • Archive or remove obsolete trivia; Git history is the recovery layer.
  • Preserve valuable public routes even when the visible navigation changes.
tip

For current AI-assisted work, start with AI Systems. Go directly to bounded agent loops for workflow design or single-GPU local models for a hardware decision; use the dated Model & API Radar only when a current hosted-product decision matters.