figassis

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.

saamerm

// YouTube Video link : https://youtu.be/MlbEel7bB8o
// Pre-reqs: Scrape the Data from the YCombinator job board (https://www.workatastartup.com/. Clean (Lint) the data to ensure it's ready for analysis.

// Code to display job listings and their corresponding salaries.
const fs = require('fs').promises;

async function printFileContents() {
    const filePath = 'yc-jobs.json';
    
    try {

moyix

#!/bin/bash

gdb -p "$1" -batch -ex 'set {short}$rip = 0x050f' -ex 'set $rax=231' -ex 'set $rdi=0' -ex 'cont'

erikig

henrik242

Disable Device Enrollment Program (DEP) notification on macOS Ventura.md

Ventura docs for M2 Macs in this comment: https://gist.github.com/henrik242/65d26a7deca30bdb9828e183809690bd?permalink_comment_id=4555340#gistcomment-4555340

Old Monterey docs in this old revision: https://gist.github.com/henrik242/65d26a7deca30bdb9828e183809690bd/32c410e3a1de73539c76fa13ea5486569c4e0c5d

Solution for Sonoma: https://gist.github.com/sghiassy/a3927405cf4ffe81242f4ecb01c382ac

fnky

holmberd

Adjusting child processes for PHP-FPM (Nginx)

When setting these options consider the following:

• How long is your average request?
• What is the maximum number of simultaneous visitors the site(s) get?
• How much memory on average does each child process consume?

Determine if the max_children limit has been reached.

• sudo grep max_children /var/log/php?.?-fpm.log.1 /var/log/php?.?-fpm.log

grimzy

#!/usr/bin/env bash

git branch -r | grep -v '\->' | while read remote; do git branch --track "${remote#origin/}" "$remote"; done
git fetch --all
git pull --all

Alex-Werner

- Install local dashcore version. 
- Create dash.conf file in .dashcore with data allowing to be requested by RPC (server=1, rpcport,... - You can use exemple [REF1] below)
- Start dashd by simply call for ./bin/dashd

- Then in another folder (insight?) do a git clone https://github.com/dashevo/bitcore-node-dash -b skip-dash-download
- cd bitcore-node-dash
- npm install
- npm install insight-api-dash --S
- npm install insight-ui-dash --S

mskvsk

<?
$entities = array('image', 'photo', 'text', 'source', 'site', 'traffic', 'money', 'book', 'e-book', 'file', 'smartphone', 'camera', 'notebook', 'cities', 'distances', 'cars', 'mobile', 'book', 'sex', 'love', 'classifieds', 'ads', 'alcohol', 'travel');
$verbs = array('sell', 'buy', 'rent', 'exchange', 'free', 'give', 'book', 'clean', 'find', 'classify', 'compare');
echo '<table style="width: 100%">';
foreach ($entities as $entity)
{
    echo '<tr>';
    foreach ($verbs as $verb)
        echo "<td style='font-size: 14px; padding: 5px; text-align: center'>$verb $entity</td>";
    echo '</tr>';