- January - 8 entries, 57 links, 10 quotes
- 2nd: Tom Scott, and the formidable power of escalating streaks
- 7th: It's OK to call it Artificial Intelligence
- 7th: Weeknotes: Page caching and custom templates for Datasette Cloud
- 9th: What I should have said about the term Artificial Intelligence
- 16th: Publish Python packages to PyPI with a python-lib cookiecutter template and GitHub Actions
- 17th: Talking about Open Source LLMs on Oxide and Friends
- 21st: Weeknotes: datasette-test, datasette-build, PSF board retreat
- 26th: LLM 0.13: The annotated release notes
- February - 4 entries, 62 links, 13 quotes
- March - 8 entries, 74 links, 12 quotes
- 3rd: Interesting ideas in Observable Framework
- 5th: Prompt injection and jailbreaking are not the same thing
- 8th: The GPT-4 barrier has finally been broken
- 16th: Weeknotes: the aftermath of NICAR
- 22nd: Claude and ChatGPT for ad-hoc sidequests
- 23rd: Building and testing C extensions for SQLite with ChatGPT Code Interpreter
- 26th: llm cmd undo last git commit - a new plugin for LLM
- 30th: Running OCR against PDFs and images directly in your browser
- April - 5 entries, 59 links, 26 quotes
- 8th: Building files-to-prompt entirely using Claude 3 Opus
- 10th: Three major LLM releases in 24 hours (plus weeknotes)
- 17th: AI for Data Journalism: demonstrating what we can do with this stuff right now
- 22nd: Options for accessing Llama 3 from the terminal using LLM
- 23rd: Weeknotes: Llama 3, AI for Data Journalism, llm-evals and datasette-secrets
- May - 5 entries, 64 links, 25 quotes
- 7th: Weeknotes: more datasette-secrets, plus a mystery video project
- 8th: Slop is the new name for unwanted AI-generated content
- 15th: ChatGPT in "4o" mode is not running the new features yet
- 28th: Weeknotes: PyCon US 2024
- 29th: Training is not the same as chatting: ChatGPT and other LLMs don't remember everything you say
- June - 7 entries, 64 links, 25 quotes
- 6th: Accidental prompt injection against RAG applications
- 10th: Thoughts on the WWDC 2024 keynote on Apple Intelligence
- 12th: A homepage redesign for my blog's 22nd birthday
- 17th: Language models on the command-line
- 19th: Weeknotes: Datasette Studio and a whole lot of blogging
- 21st: Building search-based RAG using Claude, Datasette and Val Town
- 27th: Open challenges for AI engineering
- July - 4 entries, 81 links, 35 quotes
- 2nd: Weeknotes: a livestream, a surprise keynote and progress on Datasette Cloud billing
- 13th: Give people something to link to so they can talk about your features and ideas
- 14th: Imitation Intelligence, my keynote for PyCon US 2024
- 19th: Weeknotes: GPT-4o mini, LLM 0.15, sqlite-utils 3.37 and building a staging environment
- August - 6 entries, 76 links, 22 quotes
- 5th: Datasette 1.0a14: The annotated release notes
- 6th: Weeknotes: a staging environment, a Datasette alpha and a bunch of new LLMs
- 8th: django-http-debug, a new Django app mostly written by Claude
- 22nd: Optimizing Datasette (and other weeknotes)
- 23rd: Claude's API now supports CORS requests, enabling client-side applications
- 26th: Building a tool showing how Gemini Pro can return bounding boxes for objects in images
- September - 10 entries, 49 links, 23 quotes
- 6th: Calling LLMs from client-side JavaScript, converting PDFs to HTML + weeknotes
- 8th: Teresa T is name of the whale in Pillar Point Harbor near Half Moon Bay
- 10th: Notes from my appearance on the Software Misadventures Podcast
- 12th: Notes on OpenAI's new o1 chain-of-thought models
- 18th: Things I've learned serving on the board of the Python Software Foundation
- 20th: Notes on using LLMs for code
- 25th: DJP: A plugin system for Django
- 27th: Themes from DjangoCon US 2024
- 29th: NotebookLM's automatically generated podcasts are surprisingly effective
- 30th: Weeknotes: Three podcasts, two trips and a new plugin system
- October - 12 entries, 81 links, 22 quotes
- 1st: OpenAI DevDay 2024 live blog
- 2nd: OpenAI DevDay: Let’s build developer tools, not digital God
- 15th: ChatGPT will happily write you a thinly disguised horoscope
- 17th: Video scraping: extracting JSON data from a 35 second screen capture for less than 1/10th of a cent
- 18th: Experimenting with audio input and output for the OpenAI Chat Completion API
- 19th: Running Llama 3.2 Vision and Phi-3.5 Vision on a Mac with mistral.rs
- 21st: Everything I built with Claude Artifacts this week
- 22nd: Initial explorations of Anthropic's new Computer Use capability
- 24th: Notes on the new Claude analysis JavaScript code execution tool
- 27th: Run a prompt to generate and execute jq programs using llm-jq
- 29th: You can now run prompts against images, audio and video in your terminal using LLM
- 30th: W̶e̶e̶k̶n̶o̶t̶e̶s̶ Monthnotes for October
- November - 9 entries, 65 links, 19 quotes, 1 note
- 4th: Claude 3.5 Haiku
- 7th: Project: VERDAD - tracking misinformation in radio broadcasts using Gemini 1.5
- 9th: Visualizing local election results with Datasette, Observable and MapLibre GL
- 12th: Qwen2.5-Coder-32B is an LLM that can code well that runs on my Mac
- 16th: Project: Civic Band - scraping and searching PDF meeting minutes from hundreds of municipalities
- 19th: Notes from Bing Chat—Our First Encounter With Manipulative AI
- 22nd: Weeknotes: asynchronous LLMs, synchronous embeddings, and I kind of started a podcast
- 25th: Ask questions of SQLite databases and CSV/JSON files in your terminal
- 27th: Storing times for human events
- December - 12 entries, 62 links, 26 quotes
- 4th: First impressions of the new Amazon Nova LLMs (via a new llm-bedrock plugin)
- 7th: Prompts.js
- 9th: I can now run a GPT-4 class model on my laptop
- 10th: ChatGPT Canvas can make API requests now, but it's complicated
- 11th: Gemini 2.0 Flash: An outstanding multi-modal LLM with a sci-fi streaming mode
- 19th: Building Python tools with a one-shot prompt using uv run and Claude Projects
- 19th: Gemini 2.0 Flash "Thinking mode"
- 20th: December in LLMs has been a lot
- 20th: Live blog: the 12th day of OpenAI - "Early evals for OpenAI o3"
- 22nd: My approach to running a link blog
- 24th: Trying out QvQ - Qwen's new visual reasoning model
- 31st: Things we learned about LLMs in 2024