WordPress.com’s Posts to Podcast feature turns blog posts into AI-generated audio from the dashboard. I look at how it stores the files, the media bloat risk, and how to manage the assets with WP-CLI and a theme hook.
Tightening the prompt won’t make an LLM integration reliable in production. Here’s the control layer I put between WordPress and the model: input guards, a circuit breaker, response validation and retries.
Hannah Shamji’s four levels of customer understanding, read from a developer’s side. What users say is the weakest signal, what they do is better, and the reason behind it is what you actually need to fix.
Felix Arntz and James are stepping back as Core AI Team Reps, and Jason Adams takes over. The handover lands as the Abilities API matures and the WP AI Client heads into core for WordPress 7.0.
The WordPress AI plugin 1.0.0 adds Request Logging and Connector Approvals, which give site owners real control over which plugins use AI and what they spend. Here is what changed and what developers should do about it.
A production recommender on Amazon EKS lives or dies on infrastructure, not the model. Here’s how I set up a multistage system with NVIDIA Triton, cut feature lookup latency with an in-memory cache, and scale GPU nodes with HPA and Karpenter.
Stack Overflow’s question volume has collapsed and developers now ask AI instead. I look at why AI-generated code quality is turning into a security and maintenance problem for WordPress sites, with a WooCommerce example.
The Essential Plugin attack backdoored more than 30 trusted plugins after the portfolio changed hands. I walk through how the wpos-analytics module worked, why unserialize() on remote data is so dangerous, and how WordPress.com cleaned up 2,200+ affected sites.
WordPress 7.0 is out, and the AI work behind it keeps moving. Here is what the AI contributors are working on: scaling the Abilities API, a Secrets Management API, hook-based init, and keeping C2PA metadata in the media library.
LLM-extracted themes are model outputs that only exist when a customer left text behind. Treat them as plain database columns and selection, timing and measurement error can flip the sign of your regression.