Category: Hands On
-
Computer Using AI is Solved

Two years ago I wrote an article arguing that Anthropic’s “Computer Use” – then in beta testing – would be the next ChatGPT moment for education. At the time, computer using agents (CUAs) were not common, and Anthropic’s version was strictly limited to research, running only inside a virtual computer. It had restricted access to…
-
Controlling Hardware with Generative Artificial Intelligence

Since 2024, the potential of Large Language Models (LLMs) like GPT and Claude to proficiently code has emerged as a key driver of their evolution. Their ability to integrate with both software and physical devices presents opportunities for innovative applications. This convergence of AI with everyday technology could revolutionise fields such as agritech, enhancing efficiencies…
-
How I’ve Used Claude for Book Marketing
The use of GenAI in writing, the arts, music, and pretty much any creative industry is highly contentious, and for good reason. The copyright concerns alone are enough to infuriate most writers, and the constant onslaught of AI slop is flooding social media platforms and online spaces. I’ve written extensively about my position on AI:…
-
LLMs are Digital Skeleton Keys

Skeleton keys functioned by exploiting shared mechanisms in older locks, similarly, Large Language Models (LLMs) can act as digital skeleton keys. They perform versatile tasks within code-accessible environments, yet their potential remains underutilised in conventional chatbot interfaces. Users should explore beyond chatbots to unlock LLMs’ true capabilities.
-
Building a Voice Assistant with Claude Code

I turned a $40 pocket computer into a hands-free voice assistant for Claude Code — talk to it, and a Mac mini does the thinking. Here’s how I built it.
-
IYKYK Part 2: Did You Know AI Can Do… That?

The text-box and blinking cursor of GenAI chatbot interfaces is the main thing holding us back from exploring their use. Did you know AI can do… that?
-
IYKYK: How Do We Know What AI Can Really Do?

The Discoverability Problem in GenAI means users are often unaware of capabilities due to poor UX. If the tech won’t change, we need new mental models.
-
Building Websites with Claude Code

Over the past couple of weekends I have built and published five complete websites and a complex interactive page for this site. I had the content already handy, but all of the work of making the websites, and a substantial amount of their deployment, was handled exclusively by Claude Cowork and Claude Code.
-
What is MCP and Why Should I Care?

MCP (Model Context Protocol) is a standardised way for AI assistants to communicate with external data sources and tools. I spent a weekend building my own MCP servers to connect Claude to my private data, and learned a lot about where this technology is heading.
-
Hands on with Canva Code

When Canva first launched its code tools in Canva AI, I was pretty cynical. In fact, I was definitely too harsh, with my first post based on a few basic experiments. I wasn’t impressed because I couldn’t see how it was any different to other offerings such as ChatGPT’s Canvas or Claude’s Artifacts – it…