Mac Apps
Running AI models locally used to be a niche pursuit for ML engineers. But with tools like Whisper, Ollama, and modern GPU hardware, self-hosting AI is practical for everyday developers. Here's how to set up local Whisper transcription on Mac and Windows. Why Self-Host AI? * Privacy: Your data
Privacy
Cloud meeting assistants are having a moment. Otter, Fireflies, Read.ai, and dozens of others promise to revolutionize how we handle meetings. But there are hidden costs that don't appear on their pricing pages. The Obvious Costs Let's start with what you see: ServiceMonthly CostLimitations Otter.
IoT
Healthcare software is hard. Not because the technology is particularly complex, but because the stakes are high and the regulations are strict. When I built Clearminutes, I knew it needed to work for healthcare professionals – doctors, nurses, therapists who can't just send patient discussions to random cloud services.
Python
As a developer who's spent years building cloud services, I've become increasingly skeptical of "just send it to the cloud" as the default architecture. Meeting transcription is a perfect example of where local processing makes more sense. Clearminutes — AI meetings. Zero cloud required.Local-first
Mac Apps
Like many developers, I spend hours in meetings every week. And like many developers, I've tried various meeting transcription tools: Otter.ai, Fireflies, Granola. They all share one thing in common: they send your audio to the cloud. Clearminutes — AI meetings. Zero cloud required.Local-first AI meeting transcription
GameDev
At a recent meet-up, I shared insights on shifting AAA game development to the cloud. We discussed overcoming challenges with high-performance computing, data management, and build optimisation using AWS and other tools. This move promises enhanced scalability and global collaboration.
Mac Apps
Since working from home more and having the kids around for summer holiday, my Status Light has been in more use. The status light shows the family when I'm on a call, and when I'm available to talk to. The problem was though, I was having
Python
Recently had reason to create a little currency converter app. I decided to do it it Python as I've not had the chance to use the language for a while. I didn’t want to have to build a whole UI or access a fully blown db as
IoT
Built a fully automated wifi controller for my Intex Hot Tub.
2Do
It's been a while... but the To2Do apps are being updated to work with Big Sur :) The first app (MailTo2Do) has been updated and is available here: https://bit.ly/mailto2do-v210 The other apps will be updated soon. If you'd like to donate towards my running
IoT
My goal is to create a fully automated blind, with the ability to control it via Amazon Alexa devices and Home Assistant. In order to do this I will be planning on using: * Velux KLI 310 - Solar Blind Controller * Wemos Mini D1 Micro-controller (built in Wifi & ESP8266 chip)
