⚡ Updated 07.24.23

Running notes on the mechanics, behavior, and application of large language models from our own experience as well as reading through recent AI papers & implementations (started by Mario Schlosser, @mariots, marioschlosser.org). We’ll keep updating this as new stuff comes out.


Table of contents

ℹ️ Each chapter is its own page

00 Some General Insights

Collection of take-aways from various sources inside and outside of Oscar.

01 Foundational Explanations & Capabilities

How do large language models actually work? The most recent survey/meta-research papers that discuss what LLMs have been shown to be capable of, plus an explainer of the transformer architecture (the T in GPT)

02 Prompt Engineering, or: How To Use Input Text To Control LLMs

This is where most of the action has been over the past few months - instructing LLMs to do something simply by giving it cleverly worded prompts

03 Reasoning, or: How LLMs Solve Complex Reasoning Tasks