Llm on Headtilt

AI Workflows - Visuals

Sat, 28 Feb 2026 07:52:36 +0800

It’s 2026 and I’ve been trying to decide what AI and LLMs are useful for in my day to day teaching. One of the things that has been floating around has been the promise of reducing admin time for teachers using LLMs, but I honestly haven’t found the argument to be that compelling. I don’t trust it near the things that take up most of my admin time like communicating with students, parents, and partner schools. It’s mostly been terrible for curriculum planning, mediocre at best for assessment design, and laughably bad at generating lesson slides, particularly anything involving diagrams.

WASM Python - Cat Herding 08

Tue, 14 Oct 2025 19:07:41 +0800

Pre(r)amble

This is part of a series of posts documenting some of the process of (building|cat herding an AI agent to build) Clipy, an easily hosted Python teaching tool built with just front-end JS and a WASM port of MicroPython.

You can find the GitHub repo for the project here

I keep a relatively up to date version here if you want to try it

What we had before

Last week was mostly about fixing up issues with implementation methods.

WASM Python - Cat Herding 07

Mon, 06 Oct 2025 06:10:35 +0800

Pre(r)amble

You can find the GitHub repo for the project here

I keep a relatively up to date version here if you want to try it

What we had before

Last week was adding the record-replay feature (lots more about that this week, what a rabbit hole) and putting in nicer file management (which still needs some tweaks, but I’m pretty happy with it).

WASM Python - Cat Herding 06

Tue, 30 Sep 2025 20:32:42 +0800

Pre(r)amble

This is part of a(n aspirationally) series of posts documenting some of the process of (building|cat herding an AI agent to build) an easily hosted Python teaching tool built with just front-end JS and a WASM port of MicroPython.

I have a (somewhat) up to date version of this tool running on the site. Things might occasionally be broken, things might not work the same way as they did before.

WASM Python - Cat Herding 05

Sat, 20 Sep 2025 15:08:11 +0800

Pre(r)amble

I have a (somewhat) up to date version of this tool running on the site. Things might occasionally be broken, things might not work the same way as they did before.

WASM Python - Cat Herding 04

Sat, 13 Sep 2025 05:58:07 +0800

Pre(r)amble

What we had before

See last week’s post for some of the details and screenshots.

WASM Python - Cat Herding 03

Sun, 07 Sep 2025 05:55:27 +0800

Pre(r)amble

This week I was really excited about getting the Abstract Syntax Tree feedback and testing working, as well as just tightening up the user experience a bit, hiding knobs and dials when they weren’t used, etc. I’m getting close to the end of my initial feature list!

WASM Python - Cat Herding 02

Mon, 01 Sep 2025 06:03:47 +0800

Pre(r)amble

What we had before

The outcome of the previous week’s achievements was pretty satisfying since I’d tried and failed to solve the problems of having a responsive WASM Python runtime for user code before. Being able to lean on the agent to do things like make changes to C code where I knew what the outcome needed to be, and knew how it needed to work, but didn’t know what to do to make it happen was so valuable.

WASM Python - Cat Herding 01

Thu, 28 Aug 2025 02:53:25 +0800

Pre(r)amble

I’m in a strange place in my head with respect to coding agents. On one hand I see all the really dumb stuff that “intelligent” chatbots produce, on the other hand, I’ve used them myself to turn something from “I should do that sometime when I’m motivated” into something I can actually use. It’s a weird time to be a teacher, let alone one of Digital Technologies.

Anyhow, this post (and hopefully some future ones) is an attempt to use AI to help shift some projects out of my head and backlog, and try and get them made. I’m aware of some of the things I found with my first AI coding experiment, in that rather than necessarily turning me into a “10x Engineer”, in fact it can turn me into a “0.95x Engineer”, getting me 95% of the way there and then getting stuck. The wonderful Cory Doctorow had a turn of phrase “reverse centaur” in this post, referring to when humans are forced to use AI. I loved the term, but probably not for the reason it was intended. I feel that when you’re being a centaur using AI agents, sometimes you’re the human, and sometimes you’re the horse(’s arse).

ESP-CYD

Sat, 09 Aug 2025 07:35:10 +0800

Note: There’s a companion post to this about using agentic AI here.

Pre(r)amble

I have a problem. Well, I have several problems, but this post is specifically about my habit of seeing a neat looking microcontroller, not really thinking about whether I need another one, and then buying a couple (because, well, you need two just in case, right?).

In the office I have:

A stack of v1 micro:bits
Some third party micro:bit clones
Several v2 micro:bits
Raspberry Pi Picos (2040)
DFRobot Beetles (ATmega)
DFRobot Firebeetles (ESP32)
Some ESP8266s
Various ESP32 variants (some camera versions, some plain boards)

How many have I actually gotten around to writing code on? One of the Firebeetles 😂 …and all of the micro:bits. Why? Having nice accessible inputs and outputs makes programming so much more enjoyable. The micro:bit completely nails this - no faffing around with which pin to use for the buttons, no I2C or SPI nonsense needed to poke at the accelerometer, and nothing funky to do to access the display, sound, or mic. Just use the nice simple API, load the code via USB and off you go. Even when running peripheral sensors, servos, etc the micro:bit is just a joy to get going with.

Agent Experiment

Sat, 09 Aug 2025 07:31:10 +0800

Pre(r)amble

It’s hard to avoid all the AI infesting everything these days, but apart from using completions a bit in VSCode Copilot with the occasional conversation about different libraries (which I find a pretty pleasant way to learn about new things, even if those new things are occasionally BS) I haven’t really used it for code a lot.

I read Github’s breathless “now, with AGENTS” release a while back, and never really gave it much thought until they also put out their Copilot Adventures … tutorials? The word “tutorial” feels a bit off, since the activities are couched in terms of “you’re going to make X!” but you’re not really making anything - you’re just being given examples of prompt structure to get the agent to build the thing for you.

LLMs at the Arcade

Sun, 24 Nov 2024 05:51:51 +0800

I was mentoring at our local fortnightly Coder Dojo session yesterday and heard a couple of students talking about getting help from ChatGPT. My ears pricked up because these are mostly younger kids (mid-late primary, a few in early secondary) and, as much as I try to encourage them to broaden their horizons, usually are firmly in Scratch-land, with a few who have been working in MakeCode Arcade; how were they using LLMs here?