- January - 5 entries, 29 links, 8 quotes
- Datasette 0.64, with a warning about SpatiaLite
- How to implement Q&A against your documentation with GPT3, embeddings and Datasette
- Weeknotes: AI hacking and a SpatiaLite tutorial
- Exploring MusicCaps, the evaluation data released to accompany Google's MusicLM text-to-music model
- datasette-scraper, Big Local News and other weeknotes
- February - 6 entries, 31 links, 13 quotes
- Weeknotes: A bunch of things I learned this week, plus datasette-explain
- Bing: "I will not harm you unless you harm me first"
- Analytics: Hacker News v.s. a tweet from Elon Musk
- I talked about Bing and tried to explain language models on live TV!
- In defense of prompt engineering
- Thoughts and impressions of AI-assisted search from Bing
- March - 10 entries, 46 links, 20 quotes
- Weeknotes: NICAR, and an appearance on KQED Forum
- ChatGPT couldn’t access the internet, even though it really looked like it could
- Large language models are having their Stable Diffusion moment
- Stanford Alpaca, and the acceleration of on-device large language model development
- Could you train a ChatGPT-beating model for $85,000 and run it in a browser?
- A conversation about prompt engineering with CBC Day 6
- Don't trust AI to talk accurately about itself: Bard wasn't trained on Gmail
- Weeknotes: AI won't slow down, a new newsletter and a huge Datasette refactor
- I built a ChatGPT plugin to answer questions about data hosted in Datasette
- AI-enhanced development makes me more ambitious with my projects
- April - 17 entries, 45 links, 19 quotes
- What AI can do for you on the Theory of Change podcast
- Think of language models like ChatGPT as a "calculator for words"
- Semi-automating a Substack newsletter with an Observable notebook
- Weeknotes: A new llm CLI tool, plus automating my weeknotes and newsletter
- We need to tell people ChatGPT will lie to them, not debate linguistics
- Working in public
- The Changelog podcast: LLMs break the internet
- Thoughts on AI safety in this era of increasingly powerful open source LLMs
- Running Python micro-benchmarks using the ChatGPT Code Interpreter alpha
- Prompt injection: What's the worst that can happen?
- sqlite-history: tracking changes to SQLite tables using triggers (also weeknotes)
- Web LLM runs the vicuna-7b Large Language Model entirely in your browser, and it's very impressive
- What's in the RedPajama-Data-1T LLM training set
- Data analysis with SQLite and Python for PyCon 2023
- Weeknotes: Citus Con, PyCon and three new niche museums
- The Dual LLM pattern for building AI assistants that can resist prompt injection
- Enriching data with GPT3.5 and SQLite SQL functions
- May - 12 entries, 44 links, 14 quotes
- Weeknotes: Miscellaneous research into Rye, ChatGPT Code Interpreter and openai-to-sqlite
- Let's be bear or bunny
- download-esm: a tool for downloading ECMAScript modules
- Prompt injection explained, with video, slides, and a transcript
- Midjourney 5.1
- Leaked Google document: "We Have No Moat, And Neither Does OpenAI"
- Big Opportunities in Small Data
- Weeknotes: sqlite-utils 3.31, download-esm, Python in a sandbox
- Delimiters won't save you from prompt injection
- llm, ttok and strip-tags - CLI tools for working with ChatGPT and other LLMs
- Lawyer cites fake cases invented by ChatGPT, judge is not amused
- ChatGPT should include inline tips
- June - 5 entries, 18 links, 6 quotes
- It's infuriatingly hard to understand how closed models train on their input
- Weeknotes: Parquet in Datasette Lite, various talks, more LLM hacking
- Understanding GPT tokenizers
- Symbex: search Python code for functions and classes, then pipe them into a LLM
- Weeknotes: symbex, LLM prompt templates, a bit of a break
- July - 4 entries, 20 links, 7 quotes
- August - 7 entries, 28 links, 10 quotes
- Run Llama 2 on your own Mac using LLM and Homebrew
- Catching up on the weird world of LLMs
- Weeknotes: Plugins for LLM, sqlite-utils and Datasette
- How I make annotated presentations
- Datasette Cloud, Datasette 1.0a3, llm-mlc and more
- Making Large Language Models work for you
- Datasette 1.0a4 and 1.0a5, plus weeknotes
- September - 5 entries, 35 links, 5 quotes
- October - 8 entries, 27 links, 10 quotes
- Weeknotes: the Datasette Cloud API, a podcast appearance and more
- Multi-modal prompt injection image attacks against GPT-4V
- Open questions for AI engineering
- Weeknotes: PyBay, AI Engineer Summit, Datasette metadata and JavaScript plugins
- Embeddings: What they are and why they matter
- Execute Jina embeddings with a CLI using llm-embed-jina
- Now add a walrus: Prompt engineering in DALL‑E 3
- DALL-E 3, GPT4All, PMTiles, sqlite-migrate, datasette-edit-schema
- November - 8 entries, 30 links, 15 quotes
- ospeak: a CLI tool for speaking text in the terminal via OpenAI
- Financial sustainability for open source projects at GitHub Universe
- Exploring GPTs: ChatGPT in a trench coat?
- Deciphering clues in a news article to understand how it was reported
- Weeknotes: DevDay, GitHub Universe, OpenAI chaos
- I'm on the Newsroom Robots podcast, with thoughts on the OpenAI board
- Prompt injection explained, November 2023 edition
- llamafile is the new best way to run an LLM on your own computer
- December - 7 entries, 26 links, 12 quotes
- Datasette Enrichments: a new plugin framework for augmenting your data
- Weeknotes: datasette-enrichments, datasette-comments, sqlite-chronicle
- The AI trust crisis
- Many options for running Mistral models in your terminal using LLM
- Recommendations to help mitigate prompt injection: limit the blast radius
- Last weeknotes of 2023
- Stuff we figured out about AI in 2023