Artificial Intelligence Blogs for Technologists
AI in banking, LLMs in production, AI infrastructure and governance, and what actually changes when you deploy AI at enterprise scale, written for technologists not hype-chasers.
Finally, an AI That Understands Money, Part One: Inside Revolut’s Customer Embeddings
Revolut and NVIDIA have published the most detailed public account yet of an AI that learns a customer straight from their banking history. Part one covers what it is, how it works, and what the results actually prove. This is the first of three parts. Part two looks at what it means for credit and […]
Read more →
Run Bash MCP in Claude Desktop: 1-Script Setup Guide
Andrew Baker | 01 Mar 2026 | andrewbaker.ninja You want one script that does everything. No digging around in settings. No manually editing JSON. No clicking Developer, Edit Config. Just run it once and Claude Desktop can execute bash commands through an MCP server. This guide gives you exactly that. 1. Why You Would Want […]
Read more →
The Full Context Product: How Agentic AI Redefines the Relationship Between Teams and the Software They Own
A variation on the dark factory thesis. Humans remain, humans are accountable, and what changes is everything else. 1. The Team That Memory Built There is a certain kind of organisational structure that forms not by design but by accumulated necessity. Take a low code onboarding system. It changes twice a year. It breaks twice […]
Read more →
Apple Didn’t Plan This: How the Mac mini and Mac Studio Became the AI Industry’s Favorite Workstation
A follow-up to DGX vs Mac Studio for Local LLMs: A Startup’s Guide to Choosing Your AI Hardware When I wrote the DGX vs Mac Studio comparison in June, the framing was still that a startup buys hardware for its own inference workload. Since then the story has widened considerably. It is no longer just […]
Read more →
Free AI in Every Client’s Pocket: Introducing Capitec Scam Checker
Many of the scams that hurt our clients don’t begin with an attack on our systems; they begin with a message. Over the next few weeks we’re rolling out Scam Checker, a free AI tool inside the Capitec app that lets any client send us a suspicious link, some text, a screenshot or an image […]
Read more →
AI Coding Costs Are Guesswork Without This: Instrumenting OpenCode And Claude Code
My inference bill last month was large enough to require an explanation, and my first instinct was the same one most people reach for: I had run one expensive model for everything, so the fix was to route the cheap work to a cheap model and keep the frontier model for the hard parts. That […]
Read more →
Wintel Is Dying to LinARM: How Mythos Class AI Just Tipped the Scales
Published on andrewbaker.ninja This is a researched opinion piece. The data points are sourced and linked in the references at the end, but the conclusions drawn from them are mine. I recognise that some of what follows will not be comfortable reading, particularly for teams that have built careers, processes, and significant capital programmes around […]
Read more →
The Biggest Threat to AI Investment Is AI Itself: How $700 Billion in Infrastructure Could Be Wiped Out by the Technology It Was Built to Run
There is a version of this story that the technology industry tells itself, and it goes like this: AI infrastructure spending is large, the returns will take time, but the demand is real and the economics will eventually follow. It is the same story told during the cloud buildout, and that one worked out. It […]
Read more →
Claude Code Without Model Lock In: Ghostty, OpenCode and OpenRouter
CloudScale AI SEO summary What this is: a practical build guide for running an OpenCode agent behind Ghostty, routed through OpenRouter, as an alternative to a single model coding agent such as Claude Code. Why it matters: token pricing across OpenRouter‘s catalogue varies by a factor of four to over a hundred for the same […]
Read more →
Claude Code Remote Control & Computer Use: 2026 Guide
There is a moment when a tool stops being something you use and becomes something that works for you. That moment, for Claude Code, arrived in early 2026. What began as a terminal-based AI coding assistant has evolved, in the span of a few months, into a platform capable of operating your machine, continuing its […]
Read more →
The Cloud AI Marketplace War Is Over, and AWS Won
By Andrew Baker | andrewbaker.ninja I am going to tell you that AWS won. Not in the “we had a good quarter” sense, and not in the “interesting competitive development” sense. In the final, structural sense. The kind of winning that does not get reversed in the next product cycle. I say this as someone […]
Read more →
Why AI Pilots Fail to Reach Production (And How to Fix It)
Gartner says 40% of agentic AI projects will fail by 2027. I think they’re being optimistic. Walk into almost any large enterprise right now and you’ll find the same scene: a glossy AI pilot, a proud press release, a steering committee meeting monthly to “track progress,” and an absolutely zero percent chance that any of […]
Read more →