Sitemap - 2023 - Simon Willison’s Newsletter

The AI trust crisis

Datasette Enrichments: a new plugin framework for augmenting your data

llamafile is the new best way to run a LLM on your own computer

Deciphering clues in a news article to understand how it was reported

Exploring GPTs: ChatGPT in a trench coat?

ospeak: a CLI tool for speaking text in the terminal via OpenAI

Now add a walrus: Prompt engineering in DALL-E 3

Embeddings: What they are and why they matter

Multi-modal prompt injection image attacks against GPT-4V

Talking Large Language Models with Rooftop Ruby

Build an image search engine with llm-clip, chat with models with llm chat

LLM now provides tools for working with embeddings

Making Large Language Models work for you

Datasette Cloud, Datasette 1.0a3, llm-mlc and more

Catching up on the weird world of LLMs

sqlite-utils now supports plugins

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

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

symbex: search Python code for functions and classes, then pipe them into a LLM

Understanding GPT tokenizers

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

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

llm, ttok and strip-tags - CLI tools for working with ChatGPT and other LLMs

Delimiters won't save you from prompt injection

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

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

Enriching data with GPT3.5 and SQLite SQL functions

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

What's in the RedPajama-Data-1T LLM training set

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

Running Python micro-benchmarks using the ChatGPT Code Interpreter alpha

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

Think of language models like ChatGPT as a "calculator for words"

AI-enhanced development makes me more ambitious with my projects

I built a ChatGPT plugin to answer questions about data hosted in Datasette

Could you train a ChatGPT-beating model for $85,000 and run it in a browser?

The Stable Diffusion moment for Large Language Models