Timer-XL makes the case that decoder-only Transformers beat encoders at forecasting. This looks at how TimeAttention keeps temporal order intact, why patch tokens cut the compute, and what the zero-shot numbers mean for real pipelines.
WooCommerce for Claude came out of Automattic’s Radical Speed Month. It uses MCP to give the model analytics lookup tables, a store knowledge layer and an AI-readiness score, all on one endpoint. Plus the provider pattern and how to run it locally.
Claude Code gets more reliable when it can run its own output: unit tests through WP-CLI, parallel prompts compared against the goal, and Chrome screenshots over MCP for front-end work. Also why an agent looping with no check-in is worse than no loop.
Google’s Prompt API is Chrome-only, downloads a 4GB Gemini Nano model without asking, and requires developers to acknowledge Google’s Generative AI Prohibited Uses Policy. My case against calling that a web standard.
Binary churn flags tell you that a user left but say nothing about the timing. This post covers discrete time-to-event modeling: why fixed intervals fit WordPress data, how right censoring skews a model, and a small PHP function for hazard rates.
High accuracy is the easiest number to fake. This post covers the machine learning pitfalls I keep finding in production systems: library defaults nobody checked, data leakage from scaling before the split, and metrics that ignore what the model actually decides.
One best model is one point of failure. I go through the three layers of a stacking ensemble, how predictions become features for the next layer, and what the extra training time actually costs you.
Prompt caching only pays off when the prefix stays byte-identical. I go through the mistakes that break it, a semantic cache layer for WordPress, loading tool definitions on demand, and what to keep or drop between turns.
Anthropic’s subscription ban pushed me off Claude for OpenClaw. Here is the OpenRouter setup I use with Kimi-K2.5, what it costs, where it runs slower, and the GDPR problem with hosted weights.
Automating every quick question makes tasks faster and teams weaker. What the research on informal communication and AI burnout shows, plus three ways to put useful friction back into the workflow.