AI writes the query now and I check it. That includes the time an elegant LLM-generated join pushed a production database to 98% CPU, plus the utility I use to export sanitized WooCommerce data for analysis.
The Bits-over-Random Metric compares your retrieval against random chance, which is how you catch the context pollution a high Success@K hides. Notes on staged tool routing and where the collapse regime starts.
The six-month version of this career change is a sales pitch. Coming from a software background it took closer to two years, and the money goes to people who can ship a RAG system that does not leak data, not to people who can write prompts.
A client ran her entire business through WhatsApp until the account was blocked on a Tuesday. What owned digital assets mean in practice, and why Brazil’s first Automattic partner writes WordPress.com into its contracts.
A colleague shipped a custom assistant in a couple of hours by wiring Google Calendar, Microsoft To Do and Notion together. Execution stopped being the bottleneck, and here is a Gemini API scheduler you can start from inside WordPress.
My agent failed the same caching refactor three times before I fixed how I was briefing it. Planning mode, browser access through Playwright MCP, and claude.md files are what turned that into one-shot work.
A decade of explaining why WordPress sites don’t feel like apps, and what 2026 changes: blocks described to an AI instead of scaffolded by hand, the Interactivity API handling state without page reloads, and theme.json holding the design system.
The generative AI boom is hiding a compute bottleneck. Notes on Sara A. Metwalli’s argument for quantum computing in data science, the problems QAOA handles differently, and what an offloaded optimization call could look like from a PHP hook.
A store that closes for a refresh breaks like-for-like PY reporting: the current year says Comparable and the previous year does not. Here is the SQL cursor that builds a separate PY status key, and the DAX measure that reads it.
Drift usually means a scramble for labels and a multi-hour retraining job. This is the other route: a trainable ReflexiveLayer over a frozen backbone, label-free drift triggers, and async weight updates that never block inference. It recovered 27.8 points of accuracy and cost recall.