Below is a collection of resources relevant to the AI-related research and application topics presented on these pages.

• The paper that arguably started it all: Attention is all you need by Vaswani et al.
• The paper, Sparks of Artificial General Intelligence: Early experiments with GPT-4, one of the first to discuss LLM tool use
• A collection of my (Viktor T. Toth's) notes on artificial intelligence and machine learning
• My less formal blog entries on the subject of AI and cybernetics
• A calculator for the parameter count of multihead transformers, used in language models:
  Vocabulary size V:

  Model dimension D:

  Context length C:

  Heads H:

  Layers L:

  Feedforward dim F:

  Total parameters: 0
• Brendan Bycroft's spectacular nano-GPT visualization