Simon Willison on Building with LLMs (PyCon 2025)
Came across this neat tutorial on building LLM-powered applications from Simon Willison, which he shared via his newsletter.
The materials cover practical things like setting up and running LLMs from the command line, using RAG (Retrieval Augmented Generation), and tool usage.
Here’s a snippet of the topics covered:
Topics we will cover include:
A review of the best currently available models
Using multi-modal LLMs to analyze images, audio and video
Use-cases that LLMs can be effectively applied to
How to access the most capable models via their various APIs
Prompt engineering
Retrieval Augmented Generation (RAG)
LLM tool usage
Automated evaluations for LLM applications
The latest options for running local models
Here are the tutorial materials: https://github.com/simonw/building-with-llms-pycon-2025
Found it via his newsletter here: https://open.substack.com/pub/simonw/p/building-software-on-top-of-large
