Catching up on the weird world of LLMs

I gave a talk on Sunday at North Bay Python where I attempted to summarize the last few years of development in the space of LLMs—Large Language Models, the technology …

Catching up on the weird world of LLMs Simon Willison’s Weblog Subscribe Sponsored by: Atlassian - Give your agents a plan. Not a prompt. New Jira capabilities unlock full-context for AI-native software development. Assign tasks to Claude, Cursor, or GitHub Copilot, now directly from Jira. Learn more Catching up on the weird world of LLMs 3rd August 2023 I gave a talk on Sunday at North Bay Python where I attempted to summarize the last few years of development in the space of LLMs—Large Language Models, the technology behind tools like ChatGPT, Google Bard and Llama 2. My goal was to help peo

related reading

• Stuff we figured out about AI in 2023simonwillison.net
• Making Large Language Models work for yousimonwillison.net
• Things we learned about LLMs in 2024simonwillison.net
• What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
• 2025: The year in LLMssimonwillison.net
• Productizing Large Language Modelsblog.replit.com
• GenAI Handbookgenai-handbook.github.io
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• The Llama Hitchiking Guide to Local LLMs – hackerllamaosanseviero.github.io
• Large Language Model: world models or surface statistics?thegradient.pub
• Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
• State of AI 2025: 100T Token LLM Usage Study | OpenRouteropenrouter.ai