development

September 19, 2026 by David Such Leave a Comment

Building an NFC-Powered PCB Business Card for Embedded AI

Tap a phone on the card and nine LEDs light up in sequence that emulates a neural network. The whole thing runs on whatever energy a mobiles NFC field can push into a loop of copper on a credit-card-sized PCB (about 5 mA at 2 V).

The card is to promote my new book, Embedded AI: Intelligence at the Deep Edge (No Starch Press), and Reefwing Software, the company behind it. Front Side: the book title, my name and the LED network. Back Side: Reefwing branding, a QR code, the web address and three programming pads. Both the NFC tag and the QR code point at a short URL.

The NFC business card is an open-source hardware and software project, with the design files and code released under the MIT licence. The Reefwing Software repository includes the EasyEDA schematic and PCB layout, artwork, Arduino firmware and programming instructions, so you can build your own card, adapt the design or use it as a starting point for another project. The design is still a prototype, so check the repository’s validation notes before ordering boards.

Embedded AI Book – PCBWay Offer

Five of the projects in my book on Embedded AI are built using custom PCBs: the Noise Suppression carrier board for the Raspberry Pi Pico 2, the Pico MIDI Keyboard and VS1053 Synthesizer that form the AI music project, and the Battery Monitor and Display & Logging shields that make up the battery characterization rig. These are circuits that do not work well on a breadboard, so each was designed as a proper board with the Gerbers, schematics, and bills of materials released under the MIT license. Getting them manufactured is straightforward: all five are shared projects on PCBWay with the fabrication files already attached, so ordering takes a few clicks and boards typically arrive within one to two weeks. To make building the projects even more affordable, PCBWay is offering readers a discount.

PCBWay is offering 200 readers of Embedded AI a $10 discount on orders over $30 (one use per user). Redeem the code EmbeddedAI2026 at checkout. The code is valid until April 30, 2027 (once activated, it must be used within six months). Each board costs around $5 but shipping is roughly $25 (depending on your location), so order the boards together to minimise freight, and the combined order will clear the $30 minimum.

https://www.pcbway.com/project/member/?bmbno=994A3415-F0F1-41

June 7, 2026 by David Such Leave a Comment

Why PrimalBot Needs to Sleep

In our original article on the Primal Layers framework, we described a multi-layered AI architecture inspired by the evolutionary structure of the human brain. Layer 1 (the brainstem) handles homeostasis and reflexes. Layer 2 (the limbic system) handles motivation, memory, and emotional valence. Layer 3 (the cerebellum) handles motor learning and predictive control. And the Cognitive Layer (the neocortex) handles abstract reasoning and planning.

What we didn’t address is how these layers manage knowledge over time. How does PrimalBot learn something new on Tuesday without forgetting what it learned on Monday? The answer, like so many in this project, comes from biology. And it turns out that one of the most important things a brain does is sleep.

Why Asimov’s Three Laws Shouldn’t Be the Blueprint for AI Principles

Every time a news story breaks about some new AI mishap, a chatbot lying to a user, a self-driving car making a dodgy decision, a recommendation engine nudging teenagers toward inappropriate content, someone in the comments inevitably writes, “We just need Asimov’s Three Laws.”

The trouble is that Isaac Asimov wrote the Three Laws as a plot device, not as an engineering specification. Almost every story he wrote about them was about how they fail. It is a bit like reading Jurassic Park and concluding that you now have a solid operating manual for cloning dinosaurs.

If we are serious about building safe AI, and particularly if we are building the sort of layered, bio-inspired systems that drive physical robots, we need to start from a different foundation. This article explains why, and proposes a replacement set of principles drawn from the Primal Layers framework.

Read the complete article…

April 4, 2026 by David Such Leave a Comment

Claude Code: Creating a C++ Linter for Embedded Development

I know! I’m late to the Claude Code party but now I’m here, I’m all in. If you write C++ for microcontrollers, or edge inference, you already know that the rules are different from desktop software. No heap allocation after startup. No exceptions. No recursion on a 4 KB stack. And these constraints are not optional if you want your firmware to survive.

The problem is that general-purpose linters do not enforce the rules you need. Clang-tidy is powerful, but configuring it to catch you just used int instead of int32_t, requires writing custom checks in C++ against the AST. That is a significant investment for what should be a simple rule. I wanted something I could tweak for each project.

Primal Layers — Is the Ancient Brain the Future of AI?

If you are using AI at the moment, then it is probably based on a model of the human neocortex. All of the current Large Language Models (LLMs) are overwhelmingly inspired by this approach. These architectures are great at abstract reasoning, pattern recognition, and language generation which are all tasks that are analogous to higher-order cortical functions. But is this the path to AGI? We don’t think it is, for reasons that will be explored in this article.

February 1, 2024 by David Such Leave a Comment

Adding a User Interface to ChatGPT with BeeWare — Part 1

Attempting to massage user inputs and output in ChatGPT is painful. We spent hours trying to print some coloured text using LaTeX, sometimes it works and sometimes it doesn’t. So much for no code development, we have capitulated and resorted to pulling at the Python Interpreter. Trying something new, we have wrapped our GPT-4 engine in BeeWare, which promises write once run everywhere functionality. This will also allow us to compare the OpenAI API vs browser GPT responses.

Read More – https://medium.com/@reefwing/adding-a-user-interface-to-chatgpt-with-beeware-part-1-852f1758fd65

February 1, 2024 by David Such Leave a Comment

A Review of Cross Platform Development Tools and Frameworks

It is the dream of every developer to write code once and then deploy it frictionlessly to every available platform (macOS, Windows, Linux, iOS, Android, …). This is of course very hard to do in practise, as each platform does just about everything differently. “Viva la différence!”

As consumers this is a good thing, and gives us options. As developers, it is a huge pain in the neck. Because this is a big problem for devs, a lot of people have had a crack at solving it. Every so often, we stray from the path of native development and are tempted by the sweet promise of “write once, run anywhere!” The problem is if you need to do anything close to the metal or complicated, you usually have to drop down into native code, which kind of defeats the purpose. There are some applications that are categorically not suited to cross-platform solutions. Anything that requires deep system-level integration, minimal latency, or specialized use of hardware features, probably falls into this bucket.

April 13, 2023 by David Such Leave a Comment

ChatGPT — As a Programming Tool

Although ChatGPT is unlikely to be replacing programmers anytime soon, it can be a useful coding assistant. In this article, we will investigate how you can use ChatGPT (GPT-3.5) as a programming tool, and compare it to the earlier model found in the Open AI Playground (GPT-3). For simplicity, we will use mostly Python in our examples. Despite its limitations, ChatGPT is seriously impressive.

Read more at Medium…

August 18, 2022 by David Such Leave a Comment

Age Prediction API based on First Name

I just came across an interesting API that your app can use to predict a persons age based on their first name. The API is free for up to 1000 names/day. It is called agify.io (https://agify.io/). #development

You can try it out in your browser – just insert your first name instead of “david”:

https://api.agify.io?name=david