Skip to content

Add a learning path through the pattern collection - #51

Open
devill wants to merge 1 commit into
mainfrom
add-learning-path
Open

Add a learning path through the pattern collection#51
devill wants to merge 1 commit into
mainfrom
add-learning-path

Conversation

@devill

@devill devill commented Jul 29, 2026

Copy link
Copy Markdown
Collaborator

A narrative organization of the whole collection into 12 chapters, plus the duplicate/special-case analysis behind it. Extends Lada's 27-station semantic map to every document.

Two things to decide before this leaves draft:

  • The coverage claim is stale. It says 84 documents (59 patterns). Current main has 54 patterns, and the eight pattern PRs bring it to 62 — so 87 documents. Decision Guards, External Context and Poor Person's Skill landed on main after this was written and do not appear anywhere in the path.
  • learning_path.html is a rendered view of the same content. Nothing else in the repo ships a standalone HTML file, so it may not belong here — happy to drop it and keep only the markdown.

learning_path_map.svg is not included: it disappeared from the working tree before I could commit it.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@devill
devill marked this pull request as ready for review July 30, 2026 13:36

## The story in one paragraph

You've been handed a brilliant, absurdly well-read colleague who has **no memory**, **limited attention**, **rolls dice on every answer**, **never says no**, and **you can't see what it's thinking**. The whole collection is the story of compensating for those five facts, in escalating scope: first you manage its *memory*, then its *attention*, then you learn to *verify* everything and even exploit the dice, then you turn the one-way command channel into a *dialogue*, meet it in its native *medium*, replace fragile instructions with *mechanisms*, and finally scale from one session to *systems of agents that improve themselves*. Every obstacle is one of the five facts showing up; every anti-pattern is a natural-but-wrong reaction to it; every pattern is the working counter-move.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fix: "you can't see what they're thinking" (and other instances of "it's" i this paragraph.


You've been handed a brilliant, absurdly well-read colleague who has **no memory**, **limited attention**, **rolls dice on every answer**, **never says no**, and **you can't see what it's thinking**. The whole collection is the story of compensating for those five facts, in escalating scope: first you manage its *memory*, then its *attention*, then you learn to *verify* everything and even exploit the dice, then you turn the one-way command channel into a *dialogue*, meet it in its native *medium*, replace fragile instructions with *mechanisms*, and finally scale from one session to *systems of agents that improve themselves*. Every obstacle is one of the five facts showing up; every anti-pattern is a natural-but-wrong reaction to it; every pattern is the working counter-move.

**Legend:** ⛰ obstacle (the terrain — can't be removed) · ⚠️ anti-pattern (the wrong turn) · 🧩 pattern (the move) · ↳ special case / composition marker

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd perhaps change "the wrong turn" to "the mis-step", and "the move" to "the trodden path"?


- ⛰ Limited Focus — attention dilutes or fixates
- ⚠️ Distracted Agent — one agent for everything; rules silently ignored
- ⚠️ Obsess Over Rules — piling on rules makes each one weaker

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Refers forward to "Refinement Loop" pattern

*It fabricates confidently and declares victory early. Never let output go unverified — and make verification cheap enough that you don't skip it.*

- ⛰ Hallucinations — it invents APIs (mercifully self-revealing in code)
- ⚠️ Perfect Recall Fallacy — expecting it to remember library details from training

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Forward reference to "Playgrounds" pattern. (Could be mitigated if this pattern talked about letting LLMs/Agents "Play" which then sets up "Playgrounds" perfectly...

- ⛰ Solution Fixation — first plausible hypothesis becomes "the answer"
- 🧩 **Feedback Loop** — give it a success signal and permission to iterate until green
- ⛰ Keeping Up — it generates faster than you can review
- ⚠️ Flying Blind — the surrender: skip review, vibe-code, understand nothing

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Forward reference to "Active Partner" Pattern

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants