WordPress 7.0 ships three pieces of AI plumbing: the Abilities API for registering what a site can do, the AI Client for provider-agnostic model calls, and the MCP Adapter that exposes both to assistants like Claude.
Notes from the April 8 contributor chat: the AI Client centralizes the transport layer, the Connectors page holds credentials for any service and not just AI, and the MCP adapter is close to 0.5.0.
Output entropy tells you a translation model is unsure but not why. This walks through bidirectional cross-attention, the misalignment features it exposes, and a small QE head that scores tokens without retraining the NMT model.
A walkthrough of quantum simulation in Python: a one-qubit circuit, the Hadamard gate, measurement into a classical bit, and a depolarizing noise model that makes the clean 50/50 split look more like real hardware.
Vectorless RAG is accurate, slow, and expensive to index. Proxy-Pointer RAG puts the document structure into the embeddings and metadata instead: regex skeleton trees, breadcrumbs on every chunk, and pointers back to the full section.
Reading revision numbers off 4,700 engineering drawings by hand was going to cost 160 person-hours. PyMuPDF handled every file with a text layer, GPT-4 Vision took the 1990s scans, and the batch finished in 45 minutes at 96% accuracy.
Claude Code will scaffold a WordPress plugin faster than you can spec one, which is the problem. The workflow I use: a CLAUDE.md spec first, the terminal agent second, and a manual review of everything before it ships.
An LLM pointed at a folder of documents will confidently quote a 2019 policy at a customer in 2026. What decides whether a RAG pipeline holds up is the chunking, the retrieval and the evaluation, not the model you picked.
Models trained on the output of earlier models lose the tails of the distribution and drift into nonsense. The clean data sits behind logins, and the PROPS framework is one way to train on it without anyone handing it over.
Two bad defaults for agent UIs: hide everything behind a spinner, or stream every raw log. What I map instead, and how I decide which agent decisions a user actually needs to see.