Stories by simonw

Delimiters won’t save you from prompt injection

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

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

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

AI-enhanced development makes me more ambitious with my projects

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

Don’t trust AI to talk accurately about itself: Bard wasn’t trained on Gmail

A simple Python implementation of the ReAct pattern for LLMs

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

How to read Hacker News threads with most recent comments first

Large language models are having their Stable Diffusion moment

ChatGPT can’t access the internet, even though it looks like it can

I promise ChatGPT can’t access the internet, even though it looks like it can

In Defense of Prompt Engineering

AI chatbot “Sidney” is misbehaving – Nov 23 2022 Microsoft community thread

Analytics: Hacker News v.s. a tweet from Elon Musk

Bing: “I will not harm you unless you harm me first”

Making SQLite extensions pip install-able

Exploring MusicCaps, the training data behind Google’s MusicLM text2music model

1
2
3
4
5
6
7
8
9
10