gustin gustin

name: tufte-viz description: | Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays

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.

Computer-science Reinforcement Learning got Rewards Wrong

In a recent blog post, Ben Recht described the Reinforcement Learning (RL) setup as:

Paraphrasing Thorndike’s Law of Effect, Lior defines reinforcement learning as the iterative process:

Receive external validation on how good you’re currently doing

Adjust what you’re currently doing so that you are better the next time around.

Whether or not this is how humans or animals learn, this is a spot-on definition of computer scientific reinforcement learning.

Delete unused or obsolete files when your changes make them irrelevant (refactors, feature removals, etc.), and revert files only when the change is yours or explicitly requested. If a git operation leaves you unsure about other agents' in-flight work, stop and coordinate instead of deleting.
Before attempting to delete a file to resolve a local type/lint failure, stop and ask the user. Other agents are often editing adjacent files; deleting their work to silence an error is never acceptable without explicit approval.
NEVER edit .env or any environment variable files—only the user may change them.
Coordinate with other agents before removing their in-progress edits—don't revert or delete work you didn't author unless everyone agrees.
Moving/renaming and restoring files is allowed.
ABSOLUTELY NEVER run destructive git operations (e.g., git reset --hard, rm, git checkout/git restore to an older commit) unless the user gives an explicit, written instruction in this conversation. Treat t

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

Prelude

I. Preface and Motivation

This guide was written because I don't particularly enjoy deploying Phoenix (or Elixir for that matter) applications. It's not easy. Primarily, I don't have a lot of money to spend on a nice, fancy VPS so compiling my Phoenix apps on my VPS often isn't an option. For that, we have Distillery releases. However, that requires me to either have a separate server for staging to use as a build server, or to keep a particular version of Erlang installed on my VPS, neither of which sound like great options to me and they all have the possibilities of version mismatches with ERTS. In addition to all this, theres a whole lot of configuration which needs to be done to setup a Phoenix app for deployment, and it's hard to remember.

For that reason, I wanted to use Docker so that all of my deployments would be automated and reproducable. In addition, Docker would allow me to have reproducable builds for my releases. I could build my releases on any machine that I wanted in a contai

Hitchhikers Guide to Machine Learning Resources

Reference Sources

Project Rhea — online learning community where students teach other students. The tutorials here vary in detail and quality. Generally they are more that a definition at mathworld, less than a step by step. Good for getting the highlights on an unfamiliar topic
Wolfram Mathworld — Like wikipedia, but only for Math. Go here when you have no idea what an "Isotopic Kernel is or why you would care. Mathworld will give you 80+ entries that are linked.
Wikipedia Math Portal — the place to find everything math related on Wikipedia.

	let regex;

	/* matching a specific string */
	regex = /hello/; // looks for the string between the forward slashes (case-sensitive)... matches "hello", "hello123", "123hello123", "123hello"; doesn't match for "hell0", "Hello"
	regex = /hello/i; // looks for the string between the forward slashes (case-insensitive)... matches "hello", "HelLo", "123HelLO"
	regex = /hello/g; // looks for multiple occurrences of string between the forward slashes...

	/* wildcards */
	regex = /h.llo/; // the "." matches any one character other than a new line character... matches "hello", "hallo" but not "h\nllo"
	regex = /h.llo/; // the "" matches any character(s) zero or more times... matches "hello", "heeeeeello", "hllo", "hwarwareallo"

	#!/usr/bin/env bash

	set -e

	[ -z "$CLUSTER_SECRET" ] && echo "Need to set CLUSTER_SECRET" && exit 1;

	echo 'export IPFS_PATH=/data/ipfs' >>~/.bash_profile
	echo 'export IPFS_CLUSTER_PATH=/data/ipfs-cluster' >>~/.bash_profile
	source ~/.bash_profile

	package main

	import (
	"crypto/rand"
	"encoding/base64"
	"fmt"
	"io"
	"math/big"
	)