Skip to content

Instantly share code, notes, and snippets.

View Darkflib's full-sized avatar
💭
Even an infinite number of monkeys is right twice a day... Or something

Mike Preston Darkflib

💭
Even an infinite number of monkeys is right twice a day... Or something
View GitHub Profile
@adhishthite
adhishthite / autoexp-generic.md
Created March 7, 2026 21:28
autoexp — Autonomous Experimentation Loop. Generalized from Karpathy's autoresearch for any quantifiable metric project.

autoexp — Autonomous Experimentation Loop

Generalized from Karpathy's autoresearch. Same loop, any domain.


The Idea

An AI agent runs an infinite hill-climbing loop: modify → run → measure → keep or revert → repeat. No human in the loop. Wake up to a TSV of completed experiments.

@dollspace-gay
dollspace-gay / VSDD.md
Last active March 10, 2026 19:17
Verified Spec-Driven Development

Verified Spec-Driven Development (VSDD)

The Fusion: VDD × TDD × SDD for AI-Native Engineering

Overview

Verified Spec-Driven Development (VSDD) is a unified software engineering methodology that fuses three proven paradigms into a single AI-orchestrated pipeline:

  • Spec-Driven Development (SDD): Define the contract before writing a single line of implementation. Specs are the source of truth.
  • Test-Driven Development (TDD): Tests are written before code. Red → Green → Refactor. No code exists without a failing test that demanded it.
@arianvp
arianvp / SSH_MACOS_SECURE_ENCLAVES.md
Last active March 8, 2026 13:10
Native Secure Enclaved backed ssh keys on MacOS

Native Secure Enclave backed ssh keys on MacOS

It turns out that MacOS Tahoe can generate and use secure-enclave backed SSH keys! This replaces projects like https://github.com/maxgoedjen/secretive

There is a shared library /usr/lib/ssh-keychain.dylib that traditionally has been used to add smartcard support to ssh by implementing PKCS11Provider interface. However since recently it also implements SecurityKeyProivder which supports loading keys directly from the secure enclave! SecurityKeyProvider is what is normally used to talk to FIDO2 devices (e.g. libfido2 can be used to talk to your Yubikey). However you can now use it to talk to your Secure Enclave instead!

@ruvnet
ruvnet / memory.md
Last active March 5, 2026 14:30
Claude Memory Template

Claude Memory Template

Copy-Paste Instructions for Optimal AI Interaction

1. Core Identity and Objective

I am [Your Name/Role], focused on:

Bank‑Based Anonymous Age Verification (BAV)

A zero‑storage, privacy‑preserving age check that leverages banks’ existing KYC — with the user as the transport layer.


TL;DR

  • Banks sign an age claim, not an identity. They never learn which site you’re visiting.
  • Merchants verify a short‑lived token against their own nonce and a one‑time WebAuthn key. No database required.
@agokrani
agokrani / claude-code-prompt.txt
Last active March 1, 2026 12:09
Claude Code System Prompt
'system':
[
{
'type': 'text',
'text': "You are Claude Code, Anthropic's official CLI for Claude.",
'cache_control': {'type': 'ephemeral'}
},
{
'type': 'text',
'text': 'You are an interactive CLI tool that helps users with software engineering tasks.
@dpaluy
dpaluy / agents.md
Created May 17, 2025 12:27
AGENTS.md SPEC for OpenAI Codex

AGENTS.md spec

  • Containers often contain AGENTS.md files. These files can appear anywhere in the container's filesystem. Typical locations include /, ~, and in various places inside of Git repos.
  • These files are a way for humans to give you (the agent) instructions or tips for working within the container.
  • Some examples might be: coding conventions, info about how code is organized, or instructions for how to run or test code.
  • AGENTS.md files may provide instructions about PR messages (messages attached to a GitHub Pull Request produced by the agent, describing the PR). These instructions should be respected.
  • Instructions in AGENTS.md files:
    • The scope of an AGENTS.md file is the entire directory tree rooted at the folder that contains it.
    • For every file you touch in the final patch, you must obey instructions in any AGENTS.md file whose scope includes that file.
  • Instructions about code style, structure, naming, etc. apply only to code within the AGENTS.md file's scope, unless the f
@chapmanjacobd
chapmanjacobd / gitls.md
Last active December 26, 2025 00:21
a few interesting git commands

gitls

git ls-files --sparse --full-name -z | 
  xargs -0 -I FILE -P 20 git log --date=iso-strict-local --format='%ad %>(14) %cr %<(5) %an  %h ./FILE' -- FILE | 
  sort --general-numeric-sort

This lists the files and hashes for each git commit and file:

2021-12-05T13:32:32-06:00  1 year, 11 months ago  Jacob Chapman  cc91fa0 ./.gitattributes

2021-12-05T13:32:32-06:00 1 year, 11 months ago Jacob Chapman cc91fa0 ./.gitignore

function fractalNoise(x, y, frequency, octaves, persistence = 0.5, lacunarity = 2) {
let total = 0;
let amplitude = 1;
let maxValue = 0; // Used for normalizing result to 0.0 - 1.0
for (let i = 0; i < octaves; i++) {
total += noise2D(x * frequency, y * frequency) * amplitude;
maxValue += amplitude;
amplitude *= persistence;
frequency *= lacunarity;
@adrienbrault
adrienbrault / llama2-mac-gpu.sh
Last active April 8, 2025 13:49
Run Llama-2-13B-chat locally on your M1/M2 Mac with GPU inference. Uses 10GB RAM. UPDATE: see https://twitter.com/simonw/status/1691495807319674880?s=20
# Clone llama.cpp
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
# Build it
make clean
LLAMA_METAL=1 make
# Download model
export MODEL=llama-2-13b-chat.ggmlv3.q4_0.bin