The 7.0 release went back from RC to Beta so Real-Time Collaboration data could move out of post_meta and into its own table. Also covers the WP AI Client, pseudo-states in theme.json and the Playground MCP server.
Notes from the April 8, 2026 dev chat: WordPress 7.0 makes the collaboration sync layer provider agnostic, so polling is only the default. What that means for WebSocket providers, CRDT reconciliation and block API v3.
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.
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.
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.
Gutenberg 22.9 lands background.gradient support so a gradient and a background image can coexist, adds an EmptyState component to wordpress/ui, and gives the experimental Forms block hidden input fields.
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.