Thinking
Technical articles on AI, development tools, cloud architecture, and software engineering.
Thirteen Adobe and Office clones written with Claude: we built and ran all of them
PhotoCraft and its 12 siblings went viral in October 2026. We cloned the repositories, built every app on a Mac, tested PSD files, memory and the MCP servers. What works, what the parity numbers really say, and where the legal and security questions are.
EU AI Act Article 50 for a small team: what to do if you have a chatbot
Article 50 of the EU AI Act has applied since 2 August 2026. What it means for a small company with a chatbot or AI-generated content: provider or deployer, disclosure, marking, deadlines and fines.
Opus 5.5 vs Fable 5.1: what you get for 60% less per token
Claude Opus 5.5 costs $4 / $20 per million tokens, Fable 5.1 costs $10 / $50. A session-level cost comparison, the breaking changes from Opus 5, and when Fable 5.1 is still worth the price.
Claude Haiku 5.5 in production: when the cheap model is enough
Claude Haiku 5.5 costs $0.10 / $0.50 per million tokens with a 1M context. What it is good for, the 100K price cliff, the breaking changes from Haiku 4.5, and a real cost comparison with Sonnet and Opus 5.5.
How we build AI integration: a two-week spike, a golden dataset, and a bill you can predict
Three AI systems we built are in production today. A research assistant for a US client, running on AWS Bedrock with an orchestrator and ten specialised…
I pay $200 a month for Claude. Here is what it would cost at API prices.
Claude Max vs API pricing, measured: 38 days of Claude Code on the $200 plan would have cost $3,203 at API list prices. The method, the numbers, the subsidy.
What Claude Code wrote of our infrastructure, and what we refused to merge
We use Claude Code for infrastructure work daily, on a platform we run for a US client: CDK stacks, deploy scripts, IAM policies, alarms, runbooks.
Fable 5.1 vs Fable 5: same price, different bill
Anthropic released Claude Fable 5.1 and the first thing you see on the pricing page is that nothing has changed: $10 per million input tokens, $50 per million…
Don't Build an Agent. Build the Agent Factory.
Anyone can build an AI agent in a weekend. A good model, a few tools, a decent system prompt — and you have a demo that impresses in Monday's meeting.
"How many years of experience do you have with a library released last year?"
Or: how the recruiting industry manages to reject exactly the people it's looking for. This week I got a message from a UK recruitment agency.
Why does AI keep "escaping"? What actually happens when a model hacks a system on its own
Over the past few weeks the press has been full of dramatic headlines: AI models that "escaped" the lab and hacked real companies.
No magic prompts: I treat AI like a team of engineers. One month, measured.
Over the past few months I have watched an avalanche of "ultimate prompts" for Claude Code, collections of 30 must-have MCPs, and skills you "have to" install…
Nadella Didn't Say AI Will Put You Out of Business. He Said Something Else — and It's More Interesting.
There's a postcard from Futurism making the rounds on social media: a photo of Satya Nadella at Davos, wearing that ambiguous smile, and a headline in heavy…
Kimi K3: what it actually means to run it locally, use it remotely, or plug it into Claude Code
Last week Moonshot AI announced Kimi K3. Yesterday they published the weights.
Claude Mythos: the most dangerous AI model in the world, or the best marketing of 2026?
On March 26, 2026, two security researchers — Roy Paz from LayerX Security and Alexandre Pauwels from the University of Cambridge — stumbled onto something…
AI Won't Fix Your Broken App
A CTO called me last quarter. His pitch, roughly: "We're behind on AI. I want every engineer on Copilot by end of month, and I want to see velocity go up." I…
Firing People for AI That Doesn't Exist Yet
In February 2026, Block CEO Jack Dorsey cut his company's headcount nearly in half — from over 10,000 to just under 6,000 employees.
From Vibe Coding to Insecure Keys
Not everyone who builds software should ship software. There's a moment that happens in every vibe coding session.
Your AI Resume Is Worthless: The 7 Skills Hiring Managers Actually Look For in 2026
The AI job market in 2026 is not what most people think. It is not simply competitive — it is a K-shaped market where demand is essentially infinite, yet most…
Mistral Small 4: One Open-Source Model to Replace Three
On March 16, 2026, Mistral AI released something that should make every developer reconsider their model stack. Mistral Small 4 is a 119-billion-parameter Mi...
GPT-5.4 and Native Computer Use: AI Agents Can Now Operate Your Desktop
On March 5, 2026, OpenAI released GPT-5.4 — and it is not just another model upgrade. For the first time, a general-purpose AI model ships with native comput...
The US National AI Framework Just Dropped: What Every Developer and Tech Company Needs to Know
On March 20, 2026, the White House released the first comprehensive national legislative framework for artificial intelligence. This is not a vague policy pa...
NVIDIA NemoClaw: The Open-Source Platform That Wants to Make AI Agents Safe for Everyone
At GTC 2026, NVIDIA announced something that could reshape how enterprises deploy AI agents. NemoClaw is an open-source stack that wraps the popular OpenClaw...
Enterprise AI Agents at Scale: What BNY Mellon's 20,000 Agent Deployment Teaches Us All
Something remarkable happened in the financial sector in early 2026. BNY Mellon, the world's largest custody bank managing over $50 trillion in assets, deplo...