Notes from the AI contributor meeting: AI Experiments 0.2.0 is out, the Core Post Management abilities PR is under review, PHP AI Client v0.4.0 shipped, and the MCP Adapter stays a canonical plugin. February 19 is the Beta 1 cutoff.
The WordPress AI Client is being lined up for a core inclusion proposal. January 2026 contributor notes cover streaming leaving the PHP client, a kill switch filter for locked-down sites, and MCP for tool discovery.
Prediction models find patterns; they do not tell you what an action will cause. This post walks through the causal toolkit for that: potential outcomes, DAGs, de-biasing with OLS, propensity matching, and difference-in-differences.
Cursor’s indexer is a RAG pipeline: tree-sitter splits code at logical boundaries, embeddings land in Turbopuffer, and Merkle trees keep the index in sync. Here is how the pieces fit together, and what actually leaves your machine.
For a docs bot or an internal MVP, a dedicated vector database is more infrastructure than the problem needs. Vector search is matrix multiplication, and NumPy handles it in milliseconds. Includes a small store class, the SciKit-Learn upgrade path, and the four signs you have outgrown both.
Moving a Ray job off your laptop and onto an AWS cluster: the YAML that defines the nodes, the vCPU quota that will bite you, and why ray down matters more than any tuning flag.
WP-Bench is the official WordPress AI benchmark. It runs model-written code inside a real WordPress runtime instead of asking a human whether the code looks right. How to run it, and what it still gets wrong.
Most data science applicants in 2026 are studying the wrong things and applying everywhere at once. Notes from reading hundreds of resumes: what to learn first, how to aim applications, and why referrals do the work.
SAM3 has not made custom-trained detectors pointless. Benchmarks on wheat, CCTV and blood cells show specialist models like YOLOv11 running 30x faster and scoring higher, which is why foundation models belong in development.
A side-by-side look at Azure ML and AWS SageMaker: Workspace-centric RBAC against job-level IAM roles, Datastores against raw S3 URIs, and which one holds up once training moves off notebooks.