David Cournapeau cournape

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

How are search and recommendations the same, and how are they different?

TL;DR:

The design of both search and recommendations is to find and filter information
Search is a "recommendation with a null query"
Search is "I want this", recommendations is "you might like this"

Papers

Benchmarking seems not to be a main focus of any specific academic field, although the problem has been addressed by many different groups in CS.

Some papers I found interesting:

	#!/usr/bin/env bash
	{ set +x; } 2>/dev/null

	IFS=$'\n'
	set "$@" $(find ~ -name ".*" ! -name ".CFUserTextEncoding" ! -type l -mindepth 1 -maxdepth 1) # dotfiles
	set "$@" $(find ~ -name "Google *" -mindepth 1 -maxdepth 1) # Google Drive
	set "$@" ~/git # store on github/etc :)
	set "$@" ~/node_modules

	set "$@" ~/Applications # install apps with brew cask