Skip to content

Instantly share code, notes, and snippets.

@pmarreck
pmarreck / MFIC.md
Last active July 1, 2026 05:17
MFIC — Mechanically-Falsifiable Independent Control: a discipline for enforced tests and runtime checks that keep agents honest

MFIC — Mechanically-Falsifiable Independent Control

A discipline for checks that can't be fooled by the same mistake that produced the work.

Abstract. When the author of a piece of work — an LLM, or a human moving fast — can be confidently and silently wrong, the usual defenses fail quietly: a test written from the same mistaken assumption as the code passes while the code is broken. MFIC is the class of check that escapes this trap, defined by four properties that must all hold at once. It is Mechanical (cases swept by machine, not hand-picked, so nothing is silently omitted), Falsifiable (each case genuinely bites when the work is wrong, on inputs you couldn't pre-arrange to pass), Independent (its verdict comes from the contract or the data — a source the producer doesn't control — which is segregation of duties restated for software), and a real Control (it holds the authority to block the bad outcome, not merely log it). This is the COSO / Sarbanes-Oxley model of internal co

LLM Wiki

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.

The core idea

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.

@gokusenz
gokusenz / meeting.md
Created June 27, 2026 12:10
Meeting Notes Team

Meeting Notes Team — System Prompts

ทีมนี้ทำอะไร?

ทีม AI Agent 5 ตัวที่ช่วยสรุปการประชุมอัตโนมัติ ตั้งแต่ถอดเสียง จับใจความ ดึง Action Items จัดหน้า MoM ไปจนถึงส่งสรุปเข้ากรุ๊ป


Workflow (ลำดับการทำงาน)

@facelessuser
facelessuser / exploring-tonal-palettes.md
Last active July 1, 2026 04:03
Exploring Tonal Palettes

Exploring Tonal Palettes

HCT

HCT is a color model developed by [Google][material-hct]. It aims to solve a problem related to generating color palettes with good contrast. While HCT may seem like a revolutionary color model, the idea behind it is quite simple, take the perceptually uniform color model CAM16 and combine it with the CIE Lab's lightness.

Upside of HCT

@sm86
sm86 / wprc-multiplayer-agents-a2a.md
Created June 30, 2026 22:04
WPRC NYC: Multiplayer Agents & the A2A Protocol (Shashank, Ekai Labs)
WPRC NYC : Multiplayer Agents & the A2A Protocol : Shashank (Ekai Labs) 30 Jun 2026

//1 Liner: Agents are going multiplayer. We read the A2A protocol (agent-to-agent communication, Google then Linux Foundation) as the anchor, with two shipping examples (@Claude in Slack, Paradigm's open-source Centaur). The real question: when agents go multiplayer, who owns the agent, what can it access, and can it go multiplayer ACROSS organizations? Two regimes split the room: trusted settings (inside or between known companies, shipping now) and trus

@adammb86
adammb86 / SimpleCalculator.java
Created January 6, 2020 06:59
Dibuat untuk percobaan Unit Testing di Java
public class SESimpleAdd {
static public int add(int a, int b) {
return a + b;
}
static public int multiply(int a, int b) {
return a * b;
}