Relevant Articles
Don't trust AI to talk accurately about itself: Bard wasn't trained on Gmail
Thoughts on AI safety in this era of increasingly powerful open-source LLMs
Accessing Llama 2 from the command-line with the llm-replicate plugin
Weeknotes: AI won't slow down, a new newsletter and a huge Datasette refactor
Weeknotes: A new llm CLI tool, plus automating my weeknotes and newsletter
AI-enhanced development makes me more ambitious with my projects
Semi-automating a Substack newsletter with an Observable notebook