A collection of curated learning materials about Generative AI and Large Language Models (LLMs) such as GPT-4

Since ChatGPT came onto the scene on 30th November, 2022, I've been doing a deep dive finding out what exactly LLMs and specifically ChatGPT are capable of, what their limitations are and how we can use them at Orbital Witness (the company I'm CTO at). This was obviously important since we're currently building software that 'thinks' like a lawyer using the latest natural language processing (NLP).

Given my current ongoing research on the topic, I'm going to use this blog post as a curated collection of the best content I've read across a variety of themes related to LLMs / ChatGPT / Dall-E 2 / etc. I'll update it regularly with links to new blog posts, podcasts, videos and anything else I find particularly compelling. The date in parentheses is when I added the link to this blog post and over time it will provide a change-log for easier reading.

Overview

The Large Language Model Landscape by Cobus Greyling (Nov '22 - Pre-ChatGPT)
The Near Future of AI is Action-Driven by John McDonnell (Nov '22 - Pre-ChatGPT)
Why generative AI is getting VCs all excited by Tim Smith (Jan '23)
"What Is ChatGPT Doing … and Why Does It Work?" by Stephen Wolfram (Feb '23)

Stephen also has a 3hr+ Youtube video by the same name

An Analysis of ChatGPT and OpenAI GPT-3: How to Use it For Your Business by Version 1 (Feb '23)
Who Owns the Generative AI Platform? by Matt Bornstein, Guido Appenzeller, and Martin Casado of a16z (Feb '23)
Impromptu: Amplifying Our Humanity Through AI by Reid Hoffman with GPT-4 (Mar '23)
ChatGPT: Everything you need to know about the AI-powered chatbot by TechCrunch (Mar '23)
HUGE week in generative AI by Aakash Gupta (Mar '23)
Sam Altman: OpenAI CEO on GPT-4, ChatGPT, and the Future of AI by Lex Fridman Podcast (Mar '23)
AI Notes by Latent Space Newsletter (Apr '23)
ReAct: Synergizing Reasoning and Acting in Language Models (Apr '23)
Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond (Apr '23)
Building Defensible Products with LLMs by Raza Habib (May '23)
OpenAI's plans according to Sam Altman by Raza Habib (Jun '23)
Emerging Architectures for LLM Applications by 16z (Jun '23)
The New New Moats - Why Systems of Intelligence are still the next defensible business model by Jerry Chen (Jun '23)
The New Language Model Stack by Michelle Fradin and Lauren Reeder (Jun '23)

Prompt Engineering

EMNLP: Prompt engineering is the new feature engineering by Larry Hardesty (Mar '23)
The DALL·E 2 Prompt Book by Guy Parsons (Mar '23)

a16z's podcast with Guy Parsons titled Unlocking Creativity with Prompt Engineering

Learn Prompting Course (Mar '23)
ChatGPT's API is So Good and Cheap, It Makes Most Text Generating AI Obsolete by Max Woolf (Mar '23)
Using ChatGPT with Additive Prompting for Midjourney Image Creation by Nick St. Pierre (Mar '23)
Examples of Bing Chat Prompt Engineering by Dan Berridge (Mar '23)
ChatGPT prompts to finish hours of work in seconds by Barsee (Mar '23)
Prompt Engineering by Lilian Weng (Mar '23)
Techniques to improve reliability by OpenAI Cookbook (Apr '23)
Prompt Engineering vs. Blind Prompting by Mitchell Hashimoto (Apr '23)
Fine Tuning vs Prompt Engineering Large Language Models by Niels Bantilan (May '23)

Managing Context

LlamaIndex 🦙 (GPT Index) (Mar '23)
Collection of content on the upcoming GPT4 by Life Architect (Mar '23)
OpenAI released GPT4-API: everything you need to know! by Wassim Jouini (Mar '23)

"Larger context means more complex applications: A 32k tokens context means about 25 000 words or 50 pages! This is huge! It means it can process full reports, short books or long chapters, taxation code, and so on, enabling scenarios that were impossible with ChatGPT’s 4k token limitation!"