This week we’re talking about LLMs with Simon Willison. We can not avoid this topic. Last time it was Stable Diffusion breaking the internet. This time it’s LLMs breaking the internet. Large Language Models, ChatGPT, Bard, Claude, Bing, GitHub Copilot X, Cody…we cover it all.

Simon Willison is using this year’s Advent of Code as an opportunity to learn Rust.

He’s using Copilot to help him with syntax/snippets via comment-driven prompting. He’s using ChatGPT as a study partner by asking it questions about how to do things in Rust. Is it working?

So far I think this is working really well.

I feel like I’m beginning to get a good mental model of how Rust works, and a lot of the basic syntax is beginning to embed itself into my muscle memory.

The real test is going to be if I can first make it to day 25 (with no prior Advent of Code experience I don’t know how much the increasing difficulty level will interfere with my learning) and then if I can actually write a useful Rust program after that without any assistance from these AI models.

And honestly, the other big benefit here is that this is simply a lot of fun. I’m finding interacting with AIs in this way—as an actual exercise, not just to try them out—is deeply satisfying and intellectually stimulating.

This might be an early glimpse into the future of AI-assisted learning…

Simon Willison describes the Perfect Commit as a single commit that contains all of the following:

• The implementation: a single, focused change
• Tests that demonstrate the implementation works
• Updated documentation reflecting the change
• A link to an issue thread providing further context

Here’s four paragraphs on how he got to here:

I went through a several year phase of writing essays in my commit messages, trying to capture as much of the background context and thinking as possible.

My commit messages grew a lot shorter when I started bundling the updated documentation in the commit—since often much of the material I’d previously included in the commit message was now in that documentation instead.

As I extended my practice of writing issue threads, I found that they were a better place for most of this context than the commit messages themselves. They supported embedded media, were more discoverable and I could continue to extend them even after the commit had landed.

Today many of my commit messages are a single line summary and a link to an issue!

This week on The Changelog we’re talking about Stable Diffusion, DALL-E, and the impact of AI generated art. We invited our good friend Simon Willison on the show today because he wrote a very thorough blog post titled, “Stable Diffusion is a really big deal.”

You may know Simon from his extensive contributions to open source software. Simon is a co-creator of the Django Web framework (which we don’t talk about at all on this show), he’s the creator of Datasette, a multi-tool for exploring and publishing data (which we do talk about on this show)…most of all Simon is a very insightful thinker, which he puts on display here on this episode. We talk from all the angles of this topic, the technical, the innovation, the future and possibilities, the ethical and the moral – we get into it all. The question is, will this era be known as the initial push back to the machine?

Simon Willison explains what it is:

Stable Diffusion is a new “text-to-image diffusion model” that was released to the public by Stability.ai six days ago, on August 22nd.

It’s similar to models like Open AI’s DALL-E, but with one crucial difference: they released the whole thing.

And why it’s a really big deal:

In just a few days, there has been an explosion of innovation around it. The things people are building are absolutely astonishing.

He then details some of the innovation and it is staggering, to say the least. Open FTW!

Simon Willison figured out how to run a SQL query directly against a CSV file using the sqlite3 CLI:

sqlite3 :memory: -cmd '.mode csv' -cmd '.import taxi.csv taxi' \
  'SELECT passenger_count, COUNT(*), AVG(total_amount) FROM taxi GROUP BY passenger_count'

Ie TL;DR’d the one-liner for ya, but you’ll have to go to Simon’s site for the explainer.

I love this idea by Simon Willison:

I think I’ve come up with a novel hack for the challenge of getting your company to financially support the open source projects that it uses: reach out to the maintainers and offer them generous speaking fees for remote talks to your engineering team.

It won’t work for every person and situation, but we should add it to our arsenal of ways to return economic value back to the maintainers of our open source infrastructure.

We talked with Simon Willison about Datasette on The Changelog #296. For the uninitiated, Datasette is an awesome tool for exploring and publishing data, and now you can play with it on Glitch.

The worst part of any software project is setting up a development environment. It’s by far the biggest barrier for anyone trying to get started learning to code. I’ve been a developer for more than twenty years and I still feel the pain any time I want to do something new. Glitch is the most promising attempt I’ve ever seen at tackling this problem.

This evening I decided to get Datasette running on it. I’m really impressed with how well it works, and I think Glitch provides an excellent environment for experimenting with Datasette and related tools.

Adam is on location at ZEIT Day talking with Jessica Rose about burnout, Henry Zhu about his passions and pursuit of open source, and Simon Willison about data and his passion for interesting datasets in the world.