Syntax

@syntax.fm

Tasty Treats for Web Developers with @wesbos.com @tolin.ski and @w3cj.com Brought to you by @sentry.io

The full pipeline of LLMs explained, excerpt from my video "I Built an LLM From Scratch"

The output of a transformer (LLM) is a score (logit) for every possible next token. We then use temperature, softmax, top-p and sampling to choose the next token, excerpt from my video "I Built an LLM From Scratch"

The transformer architecture that powers modern LLMs explained, excerpt from my video "I Built an LLM From Scratch"

Token embeddings explained, excerpt from my video "I Built an LLM From Scratch"

A brief history of neural networks, excerpt from my video "I Built an LLM From Scratch"