Show your work.
Primary sources, runnable code, screenshots of failure. Make claims easy to inspect.
DOCUMENTS → GRAPH → UNDERSTANDING
An evolving knowledge workspace that extracts concepts, preserves evidence, and lets you project the same understanding into Obsidian.
By default, extraction runs in this browser. If you configure a same-origin model endpoint, the graph is still yours, the evidence stays attached, and every pass becomes a revision you can inspect or export.
Your graph will appear here.
Nodes are concepts. Lines are evidence.
Export a navigable Markdown projection with YAML frontmatter,
backlinks, relation lists, and source evidence. Open it in
Obsidian, open the included native Graph.canvas
view, edit the notes, and bring corrections back as feedback.
Full exports include source text, evidence quotes, and source URIs. Use the redacted actions for public sharing.
Ingest a document to generate an Obsidian projection.
A document is useful once its ideas can be found, connected, and challenged. The workbench turns unstructured text into a transparent internal representation instead of hiding the path behind a single answer.
The loop is: ingest → infer → inspect → improve → project. The graph is not the final truth. It is a living hypothesis with evidence attached and a revision history.
Start anywhere. The map is arranged by dependency, not prestige. The best next note is usually the one that makes your current project less mysterious.
No notes match that search. Try a broader question.
A deliberately small syllabus for building intuition through contact. You do not need to finish every exercise. You do need to keep making things.
Take a text file you care about. Build a tokenizer. Train a small transformer. Watch the loss curve move. Then make it fail in three interesting ways.
See the build brief ↗# the loop is the lesson
for step in range(max_steps):
xb, yb = get_batch()
logits, loss = model(xb, yb)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print(f"step {step}: {loss.item():.3f}")
These are not commandments. They are useful constraints for a fast-moving field.
Primary sources, runnable code, screenshots of failure. Make claims easy to inspect.
The smallest useful explanation beats the grand unified theory every time.
Performance, cost, latency, data, and weird behavior are part of the concept.
Every page should give the next curious person somewhere concrete to start.
The best version of this resource cannot be written by one person. Add a correction, a sharper analogy, a benchmark, a failed attempt, or a link that deserves more context.