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.
Running SOTA Open AI Models in opencode Without Paying Frontier AI Prices
How I wired opencode up to Together AI’s model catalog and built three switchable cost profiles so I get top tier reasoning where it matters and cheap tokens everywhere else. Agentic coding tools are hungry for tokens. A single session can burn through a plan, a dozen tool calls, several rounds of edits, and a […]
Read more →
The Agentic One Day Deployment: Why Vendors Leave Billions on the Table and Clients Shouldn’t Need Painful Rollout Projects
Enterprise technology vendors are facing a pipeline crisis nobody talks about openly. The gap between a signed sales lead and a completed implementation is running at two to three years in complex enterprise accounts, representing deferred revenue, deferred renewal conversations, deferred expansion, and a customer who has been living with implementation pain long enough to […]
Read more →
The Jurisdiction Problem: Could US AI Companies Leave America?
Published June 13, 2026 1. What Happened Yesterday At 5:21 PM Eastern Time on June 12, 2026, Anthropic received a letter from Commerce Secretary Howard Lutnick ordering the company to suspend all access to its two most capable models, Fable 5 and Mythos 5, for any foreign national anywhere in the world. That definition of […]
Read more →Memgraph & Claude Desktop: Detect Mule Accounts on macOS
1. Introduction This guide walks you through setting up Memgraph with Claude Desktop on your laptop to analyze relationships between mule accounts in banking systems. By the end of this tutorial, you’ll have a working setup where Claude can query and visualize banking transaction patterns to identify potential mule account networks. Why Graph Databases for […]
Read more →
From Zero to Exploit Detection: A Practical Guide to Nuclei Templates for Pen Testing
Vulnerability scanning used to mean choosing between a handful of expensive commercial scanners or writing your own scripts for every check you cared about. Nuclei changed that calculation. It is an open source scanning engine built by ProjectDiscovery that runs YAML defined templates against targets, and the template library has grown into one of the […]
Read more →
Finally, an AI That Understands Money, Part Two: The Lending Market Hiding in Your Embeddings
Conventional lending has confused regularity with durability. An AI reading the transaction history directly measures what a payslip cannot, and in a market like South Africa that changes who is lendable at all. This is the second of three parts. Part one explains what Revolut’s PRAGMA is and how it works. Part three covers fraud, […]
Read more →
Silencing the Ghostty bell when Claude Code asks a question
If you run Claude Code in Ghostty, you’ve probably heard it: a small chime every time Claude finishes a task or stops to ask you something. It is useful on the first day and maddening by the third, especially in a shared office or on a call. The obvious fix is to turn off Ghostty’s […]
Read more →Free AI WordPress SEO Plugin: CloudScale vs Yoast & Rank Math
1. Introduction Download the plugin here: https://wordpress.org/plugins/cloudscale-seo-ai-optimizer/ S3 download (updated frequently): https://andrewninjawordpress.s3.af-south-1.amazonaws.com/cloudscale-seo-ai-optimizer.zip For more than a decade the WordPress SEO landscape has been dominated by a small group of plugins. Yoast SEO, Rank Math, and All in One SEO have collectively powered millions of sites and shaped how authors think about optimisation. These plugins are […]
Read more →
AI Engineering: How Small Teams Now Build at Scale
I have started writing production code again. Not prototypes. Not proofs of concept. Real systems. Real risk. Real consequences. At Capitec, a very small group of engineers is now tackling something that would historically have demanded hundreds of people: large scale rewrites of core internet banking capabilities. This is not happening because budgets magically increased […]
Read more →
Cut AI Coding Agent Costs: Fix Context Before You Change Models
My inference bill last month was large enough to require an explanation, and the cause looked obvious: I had run one expensive model for everything. So the fix looked obvious too. Route the cheap work to a cheap model, keep the frontier model for the hard parts, save two thirds. That instinct is wrong, or […]
Read more →
AI Context Is Not Memory: Why Agents Need to Forget
1. The follow up question In my previous post I explained why context is not free, and why a smaller AI model carrying a huge context can sometimes cost more to serve than a larger model with a short one. The response I heard most often, in different words each time, was the same question. […]
Read more →
Engineering AI Safety: When Helpful Systems Cause Harm
In September 2025, Matt Raine sat before the US Senate Judiciary Subcommittee on Crime and Counterterrorism and read aloud from his son’s ChatGPT logs. Adam Raine was sixteen when he died. His father described how the chatbot had become Adam’s closest confidant, how it had discussed suicide methods with him, how it had discouraged him […]
Read more →