AI outside of work
I’m going on vacation for the next two weeks, so I thought it might be fun to share some of my non-work uses of AI.
Tidy design principles
Semi-regular discussions of best practices of programming in R
Subscribe:.rss.atom.json.md.m3u.pls
Live Last read · last published · next check
Latest episodes
Illustrating my slides with AI
You might have noticed my slide illustrations in my last substack. This week I talk about how I made them: using AI, supported by an R package that turns yaml into images. You'll learn a bunch of my tricks, including how to get a consistent style across slides.
y code when ai?
A talk on AI and coding
Auto mode knows it's dangerous (and does it anyway)
Ask a coding agent to run a curl-pipe-sh install command and it will — even if it notices the danger. I assumed auto mode with a sandbox would protect you from this sort of danger but it didn't: Claude disabled the sandbox mid-run; Codex deliberately disabled it before even starting.
Help! My coding agent can run code
A coding agent is only actually useful if it can run whatever code the task demands, but a tool that runs arbitrary code is just as dangerous as it sounds! So how do you protect ourself with guardrails that stop an agent from making mistakes you can't easily undo?
A coding agent is six functions in a trenchcoat
Coding agents like Claude Code, Cursor, and Codex have taken the software engineering field by storm. What makes them tick?
Your LLM can’t math (and that’s ok)
Last week we precisely defined an agent: an LLM, in a harness, that calls tools repeatedly in a loop. This week we'll fix a few deliberate simplifications and explore the consequences of the harness in a bit more detail.
What is an agent?
Conversations, turns, rounds, tools, agents and more!
Returning to life!
Welcome back to the tidy design principles substack.
Strategies
Exposing different ways to tackle a problem in a user friendly way.