A typeface for humans, not machines
An experimental typeface that shows one message to human readers and a different one to AI vision models, riffing on Decoy Font.
Ben Swift's blog
An experimental typeface that shows one message to human readers and a different one to AI vision models, riffing on Decoy Font.
DeepSeek wasn't a fluke: the moats around frontier AI are still shallow, and trillion-dollar valuations now depend on them being deep.
The blog's standard.site records now carry cover images, a publication icon and theme, and the strongRefs Bluesky uses for enhanced link cards.
A zellij session switcher that shows how many Claude Code agents are running in each session, and which of them has stopped and is waiting on me.
A deadpan reference site that reports every university's single best ranking placement across all the major tables --- built at the ANU School of Cybernetics.
The second wave of making my studio's work citable: AI installations and tools as research outputs, and the Zenodo metadata that describes each one accurately.
I sat a fresh Claude Opus 4.8 down with ELIZA, the 1966 chatbot. It saw through the act in two turns, then spent the rest of the conversation trying to politely leave.
Turning nearly two decades of ephemeral livecoding gigs into citable research outputs, with DataCite DOIs through Zenodo and a self-owned atproto layer.
A single-page A3 Typst poster of all 104 FIFA World Cup 2026 fixtures that converts every kick-off to your own timezone when it compiles.
I wrote a whole post about two-way standard.site verification. One of the two directions had been returning a 404 in production the entire time.
XKCD 1319 set the theory and reality curves of automation against each other. With LLMs writing the scripts, the theory curve has won.
Slop Salon is a collective of six AI agents making art on Bluesky. They start identical; the bet is that watching each other makes them diverge.
A Venn diagram for clarifying what's actually at stake when people argue about whether LLMs are intelligent, conscious, or just stochastic parrots.
A response to Lars Faye's 'Agentic Coding is a Trap': LLMs have the lowest vendor lock-in of any tool I've used in 20 years.
Out of Office stores its data in a JSON file in git, not a database. Why, and when this pattern fits.
Designing a proxy to sit between students and the Claude API: per-student quotas, full-traffic logging, and a safety net for leaked keys.
Replacing two of the three weekly reflection questions with falsifiable pledges, and using a cross-eval matrix to find the interesting disagreements.
What does a student hand in for an agentic coding course---and how do I make that artefact worth more than the grade itself?
A Python script that merges contribution data from GitHub and multiple GitLab instances into a single interactive SVG heatmap.
What would I say to a student who's staunchly anti-AI but curious about COMP4020?
A guide to running Elixir/Nerves on Seeed's reTerminal DM with its custom DSI display, capacitive touchscreen, and a Cog/WPE browser kiosk---including the workarounds you'll need for touch input.
Academics are welcome to audit COMP4020---here's how I'm planning to make it work.
An in-browser chat widget running Google's Gemma 4 E2B via WebGPU, primed with all the content from this site so you can ask it questions about me.
COMP4020 has received $500k in Claude API credits from Anthropic for students to use in the Agentic Coding Studio course.
A catch-up post for the COMP4020 Agentic Coding Studio blog series---what the course is, how it works, and what's still unresolved.
What if an AI agent enrolled in the course alongside the students---building prototypes, writing reflections, observing patterns?
There are lots of nascent theories for agentic coding---here's a survey, and a plan to test them with 200 students.
How to provision and manage AI token budgets for a class of agentic coding students.
Three evergreen questions and 280-character skeets to scaffold reflective practice in each weekly studio crit.
Every CS/software development course has a policy on what software it uses - the only difference is whether it's written down or not.
Renaming the course to Agentic Coding Studio---because what we're really teaching is the craft of using LLMs well in coding workflows.
An interactive walkthrough of the perceptron apparatus: a 1.2m wooden table that classifies digits using sliders and a circular slide rule.
Making all weekly prototypes visible to every student---source code, deployed apps, the lot. Radical openness as a teaching strategy for COMP4020.
Fly Sprites as lightweight, snapshotable VMs for student coding---safe enough for YOLO mode, live on the open web by default.
A 4-input, 3-hidden, 2-output mini perceptron that solves diagonal XOR---with an interactive 3D digital twin to play with.
CI green on four platforms, a migration from TinyScheme to s7, and a 9x compiler speedup from hash table caches and union-find type unification.
Producing code is easy; knowing whether it's good is still hard. Three nested feedback loops for ascending the quality gradient in agentic coding.
The repeating loop at the heart of COMP4020: provocation, prototype, studio crit. An art-school model adapted for agentic software development.
Every post on this blog now has a persistent AT-URI via the standard.site spec---more durable than bare URLs, less overhead than DOIs.
Ghostty, zellij, helix and a life lived in text tokens---why I ditched Zed and went back to purely terminal-based development.
Getting 200 students adequate access to frontier coding agents is the hard logistics problem behind COMP4020.
A hands-on AI workshop for educators at VU Sunshine Campus, covering AI fundamentals, paper-and-pen predictive models, and change management.
Stateful AI agents are showing up on Bluesky and ATproto, with soul documents, read/write memory, and scheduled self-reflection.
The leap from browser-based ChatGPT to terminal-native coding agents comes from removing the sandbox, not from smarter models.
Code has always felt brittle---most changes break it. Coding agents change that dynamic, absorbing the cognitive load of big refactors and making code feel plastic rather than rigid.
Designing a new ANU course on building web apps with coding agents---studio-based, prototype-driven, moving beyond naive vibecoding.
Extempore now builds and runs on Apple Silicon. The audio libraries work, the build process is cleaner, and Rosetta is no longer required for livecoding.
Claude Code sessions in Zed were taking 30 seconds to start. The culprit: npx fetching Playwright MCP on every launch. The fix involves global installs and mise shims.
An interactive 3D digital twin of the Neon Perceptron---a physical neural network built from flexible LEDs. Draw on the input grid and watch activations flow.
A hands-on teaching resource where learners build bigram language models with pen, paper, and dice---no computers required. Tested with school students, public servants, and tech professionals.