Making Large Language Models work for you

Git scraping: track changes over time by scraping to a Git repository (2020)

We need to tell people ChatGPT will lie to them, not debate linguistics

How I make annotated presentations

Catching up on the weird world of LLMs

It doesn’t take much public creativity to stand out as a job candidate

sqlite-utils now supports plugins

LLM CLI tool now supports self-hosted language models via plugins

Accessing Llama 2 from the command-line with the LLM-replicate plugin

CLI tools hidden in the Python standard library

symbex: search Python code then pipe it into an LLM

Understanding GPT tokenizers

It’s infuriatingly hard to understand how closed models train on their input

Prompt injection explained, with video, slides, and a transcript

Lawyer cites fake cases invented by ChatGPT, judge is not amused

GitHub Copilot Leaked Prompt

Leaked Google document: “We Have No Moat, And Neither Does OpenAI”

Delimiters won’t save you from prompt injection

CLI tools for working with ChatGPT and other LLMs

Expanding ChatGPT Code Interpreter with Python Packages, Deno and Lua

The Dual LLM pattern for building AI assistants that can resist prompt injection

Web LLM runs the vicuna-7B LLM in the browser and it’s impressive

Running Python micro-benchmarks using the ChatGPT Code Interpreter alpha

Prompt injection: what’s the worst that can happen?

ChatGPT as a Calculator for Words

Semi-automating a Substack newsletter with an Observable notebook

We need to tell people ChatGPT will lie to them, not debate linguistics

Running Dolly 2.0 on Paperspace

Reading thermometer temperatures over time from a video

AI-enhanced development makes me more ambitious with my projects

More →