GPU starvation, not GPU speed, is what slows most training runs. How I find AI/ML data transfer bottlenecks in an nsys trace, then fix them with num_workers, pinned memory and a CUDA stream prefetcher.
WordPress AI Client v0.4.0 rewrites the Google, Anthropic and OpenAI providers, adds PSR-14 events and a caching layer. What that means for plugin authors ahead of the February 19th Beta 1 for Core 7.0.
WordPress now has WP-Bench, a benchmark that tests AI models on Core APIs, security patterns and block development. It runs the generated code in a real WordPress runtime instead of grading answers on paper.
Gutenberg 22.3 is the first clear look at the WordPress 7.0 developer features: combined grid controls, a dedicated Fonts screen, and PHP-only block registration. Here is what each one changes on a production site.
AI can write a WooCommerce feature in seconds, and it usually writes it as one 150-line God function with a hard-coded API key. This is what that debt costs and how to refactor it into something maintainable.
The January WooCommerce developer office hours land on Slack on January 21, 2026, with no agenda. It is an hour for holiday war stories, stubborn bugs, and whatever people want to see on the 2026 roadmap.
Notes from the Web Directions Dev Summit in Sydney, where the argument was that CSS scroll-driven animations make most JS scroll libraries pointless. Includes the CSS, and why prefers-reduced-motion is not optional.
Hardcoded API keys hold up until the first model deprecation. Here is how I use AWS Bedrock as the gateway instead: Boto3 calls, inference profiles, IAM permissions, and a triage assistant that runs on Lambda rather than inside the WordPress request cycle.
Chatting with an LLM in a browser tab is a bottleneck. This is the Claude Code setup I use instead: slash commands for the prompts I repeat, an AGENTS.md file for project memory, and plan mode before any code gets written.
Longer context windows cost server memory, not just compute. Infini-attention replaces the growing KV cache with a fixed-size compressive memory matrix updated by a Delta Rule, which cut memory use by 114x in Google’s tests.