Archive for 2023
- 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, 45 links, 20 quotes
- Weeknotes: NICAR, and an appearance on KQED Forum
- ChatGPT can't access the internet, even though it really looks like it can
- 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 - 10 entries, 42 links, 13 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"
- 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