Jeffrey Arnold jrnold

Comparison of ZSH frameworks and plugin managers

Changelog

update 1: add a FAQ section
update 2: benchmark chart and feature comparison table
update 3:
- improve the table with missing features for antigen
- new zplg times result

TLDR

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

Agent Guidelines for Python Code Quality

This document provides guidelines for maintaining high-quality Python code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

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.

	# code to understand product terms and probit models

	# clear workspace
	rm(list = ls())

	# load packages
	library(tidyverse)
	library(plotly)

	# parameters

	#!/usr/bin/env python3
	# /// script
	# requires-python = ">=3.9"
	# dependencies = [
	# "httpx",
	# "typer",
	# "rich",
	# ]
	# ///
	"""