Sitemap - 2024 - Simon Willison’s Newsletter

Things we learned about LLMs in 2024

QvQ - Qwen's new visual reasoning model

December in LLMs has been a lot

Gemini 2.0 Flash "Thinking Mode"

Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi streaming mode

I can now run a GPT-4 class model on my laptop with Llama 3.3 70B

First impressions of the new Amazon Nova LLMs

Ask questions of SQLite databases and CSV/JSON files in your terminal

Civic Band - scraping and searching PDF meeting minutes from hundreds of municipalities

Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac

VERDAD - tracking misinformation in radio broadcasts using Gemini 1.5

Claude 3.5 Haiku

Run prompts against images, audio and video in your terminal using LLM

The new Claude analysis JavaScript code execution tool

Anthropic's new Computer Use capability

Everything I built with Claude Artifacts this week

Video scraping using Google Gemini

Gemini 1.5 Flash-8B, FLUX 1.1 Python 3.13...

OpenAI DevDay: Let’s build developer tools, not digital God

NotebookLM's automatically generated podcasts are surprisingly effective

Llama 3.2 and plugins for Django

OpenAI's new o1 chain-of-thought models

Building a tool showing how Gemini Pro can return bounding boxes for objects in images

Claude's API now supports CORS requests, enabling client-side applications

django-http-debug, mostly written by Claude

Datasette 1.0a14: The annotated release notes

Llama 3.1, now available in LLM

GPT-4o mini, LLM 0.15, sqlite-utils 3.37 and building a staging environment

Imitation Intelligence keynote at PyCon 2024

Open challenges for AI engineering

Building search-based RAG using Claude 3.5 Sonnet, Datasette and Val Town

Language models on the command-line

Thoughts on the WWDC 2024 keynote on Apple Intelligence

Accidental prompt injection against RAG applications

Training is not the same as chatting: ChatGPT and other LLMs don't remember everything you say

ChatGPT in 4o mode doesn't have the new voice and image features yet

GPT-4o, a new version of LLM and more thoughts on slop

LLM slop, datasette-secrets, llm-evals, gpt2-chatbot and a whole lot more

Options for accessing Llama 3 from the terminal using LLM

AI for Data Journalism: demonstrating what we can do with this stuff right now

Three major LLM releases in 24 hours

Building files-to-prompt entirely using Claude 3 Opus

Building and testing C extensions for SQLite with ChatGPT Code Interpreter

Claude and ChatGPT for ad-hoc sidequests

The GPT-4 barrier has finally been smashed

Interesting ideas in Observable Framework

The killer app of Gemini Pro 1.5 is video

Datasette 1.0a8: JavaScript plugins, new plugin hooks and plugin configuration in datasette.yaml

LLM 0.13: The annotated release notes

Talking about Open Source LLMs on Oxide and Friends

Stuff we figured out about AI in 2023