Luis Armendariz ludwig

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

Mandelbrot in Mojo with Python plots

Not only Mojo is great for writing high-performance code, but it also allows us to leverage huge Python ecosystem of libraries and tools. With seamless Python interoperability, Mojo can use Python for what it's good at, especially GUIs, without sacrificing performance in critical code. Let's take the classic Mandelbrot set algorithm and implement it in Mojo.

We'll introduce a Complex type and use it in our implementation.

Mandelbrot in python

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

Setup HashiCorp Vault on docker

Vault secures, stores, and tightly controls access to tokens, passwords, certificates, API keys, and other secrets in modern computing. Vault is primarily used in production environments to manage secrets. Vault is a complex system that has many different pieces. There is a clear separation of components that are inside or outside of the security barrier. Only the storage backend and the HTTP API are outside, all other components are inside the barrier.

Figure 1: Architecture of Vault and Spring App (Click to enlarge)

The storage backend is untrusted and is used to durably store encrypted data. When the Vault server is started, it must be provided with a storage backend so that data is available across restarts. The HTTP API similarly must be started by the Vault server on start so that clients can interact with it.

CUSTOM GAME ENGINES: A Small Study

A couple of weeks ago I played (and finished) A Plague Tale, a game by Asobo Studio. I was really captivated by the game, not only by the beautiful graphics but also by the story and the locations in the game. I decided to investigate a bit about the game tech and I was surprised to see it was developed with a custom engine by a relatively small studio. I know there are some companies using custom engines but it's very difficult to find a detailed market study with that kind of information curated and updated. So this article.

Nowadays lots of companies choose engines like Unreal or Unity for their games (or that's what lot of people think) because d

Simple Vault TLS Certificate validation & testing

Set of scripts to deploy locally, vault and configure TLS server and user certificates for testing TLS AUTH.

credit to @reard3n (https://github.com/reard3n) and @v6 (https://github.com/v6) for the gist this grew from

Notes

This was tested using Vagrant and Ubuntu

Getting Setup

On the OS of your choice copy VaultCASetup.sh script locally and update any variables that would be specific to your environment and/or


	function mandelbrot_kernel(c, max_iter)
	z = c
	for i in 1:max_iter
	z = z * z + c
	if abs2(z) > 4
	return i-1
	end
	end
	return max_iter

	import requests
	import time
	import os
	import sys
	import openai
	import tiktoken
	from termcolor import colored

	openai.api_key = open(os.path.expanduser('~/.openai')).read().strip()

	BUCKET_NAME=terraform-your_company-remote-store # this should be unique, and by that I mean really UNIQUE
	BUCKET_REGION=eu-central-1
	USER_NAME=terraform-deployer
	POLICY_FILE_NAME=$PWD/policy.json
	AWS_PROFILE=your_company

	aws s3api create-bucket \
	--profile $AWS_PROFILE \
	--bucket $BUCKET_NAME \
	--region $BUCKET_REGION \