Mapping self-replicating systems from fiction to your factory architecture.
Tommy Williams wommy
dan-myles
/ bun-effect.ts
Last active
August 17, 2026 16:56
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /** | |
| * Minimal Effect test wrapper for Bun's native test runner. | |
| * | |
| * This provides `it.effect()` and `it.scoped()` that work with `bun test`, bun's native test runner, | |
| * similar to `@effect/vitest`. When the official `@effect/bun-test` package | |
| * is released, replace this with that package. | |
| * | |
| * @see https://github.com/Effect-TS/effect/pull/5973 | |
| * | |
| * @example |
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
bdmorin
/ prompt-dna-mario-zechner.md
Created
April 16, 2026 03:22
The Prompt DNA of Mario Zechner — A psychological analysis of 2,796 prompts across 626 coding-agent sessions from the pi-mono public transcripts
How does an expert software developer actually talk to an AI coding agent? We analyzed 2,796 prompts across 626 sessions from @badlogic's publicly shared pi-mono transcripts. The answer is: like a startup founder talking to a senior dev who keeps overstepping.
OlderNewer