/ai-notes

notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.

MIT LicenseMIT

AI Notes

notes on AI state of the art, with a focus on generative and large language models. These are the "raw materials" for the https://lspace.swyx.io/ newsletter.

This repo used to be called https://github.com/sw-yx/prompt-eng, but was renamed because Prompt Engineering is Overhyped. This is now an AI Engineering notes repo.

This Readme is just the high level overview of the space; you should see the most updates in the OTHER markdown files in this repo:

  • TEXT.md - text generation, mostly with GPT-4
    • TEXT_CHAT.md - information on ChatGPT and competitors, as well as derivative products
    • TEXT_SEARCH.md - information on GPT-4 enabled semantic search and other info
    • TEXT_PROMPTS.md - a small swipe file of good GPT3 prompts
  • INFRA.md - raw notes on AI Infrastructure, Hardware and Scaling
  • AUDIO.md - tracking audio/music/voice transcription + generation
  • CODE.md - codegen models, like Copilot
  • IMAGE_GEN.md - the most developed file, with the heaviest emphasis notes on Stable Diffusion, and some on midjourney and dalle.
    • IMAGE_PROMPTS.md - a small swipe file of good image prompts
  • Resources: standing, cleaned up resources that are meant to be permalinked to
  • stub notes - very small/lightweight proto pages of future coverage areas - AGENTS.md - tracking "agentic AI"
  • blog ideas- potential blog post ideas derived from these notes
Table of Contents

Motivational Use Cases

Top AI Reads

The more advanced GPT3 reads have been split out to https://github.com/sw-yx/ai-notes/blob/main/TEXT.md

Beginner Reads

Intermediate Reads

Advanced Reads

We compared 126 keyword modifiers with the same prompt and initial image. These are the results.

other lists like this

Communities

People

This list will be out of date but will get you started. My live list of people to follow is at: https://twitter.com/i/lists/1585430245762441216

Quotes, Reality & Demotivation

Legal, Ethics, and Privacy

Alignment, Safety

regulation

  • chinese regulation https://www.chinalawtranslate.com/en/overview-of-draft-measures-on-generative-ai/
  • italy banning chatgpt
    • At its annual meeting in Japan, the Group of Seven (G7), an informal bloc of industrialized democratic governments, announced the Hiroshima Process, an intergovernmental task force empowered to investigate risks of generative AI. G7 members, which include Canada, France, Germany, Italy, Japan, the United Kingdom, and the United States, vowed to craft mutually compatible laws and regulate AI according to democratic values. These include fairness, accountability, transparency, safety, data privacy, protection from abuse, and respect for human rights.
  • U.S. President Joe Biden issued a strategic plan for AI. The initiative calls on U.S. regulatory agencies to develop public datasets, benchmarks, and standards for training, measuring, and evaluating AI systems.
  • Earlier this month, France’s data privacy regulator announced a framework for regulating generative AI.

Misc