Part 2 of the SageMaker vs Azure ML series, this time on compute. Azure keeps clusters as persistent workspace assets while SageMaker spins them up per job and tears them down after, plus spot instances, checkpointing and container control.
A Pandas iterrows() loop over 3.5 million flight records took about 170 seconds. py-spy is a sampling profiler that shows where the time went without slowing the script down, and the vectorized NumPy rewrite does the same work in 0.56 seconds.
loc selects by label, iloc by position, and their slicing rules disagree: loc includes the stop value, iloc excludes it. Here is when I use each one, plus the duplicate-index case where loc quietly breaks a model.
Separate repos for the React frontend and the WordPress backend are why payloads drift out of sync. Notes on moving to a monorepo with Roots Bedrock, keeping an AGENTS.md map of endpoints for coding agents, and the stale REST cache that broke a checkout.
Pre-built agent toolboxes break the moment a client asks something you did not plan for. Here is the plan-code-execute setup I use instead, where the agent writes its own Python, plus the hallucinated CSV that taught me why the analyst step is mandatory.
Freshly Pressed is back in the WordPress.com Reader, with people picking the posts instead of an engagement score. If you are self-hosted, that only helps once your Jetpack sync is actually working, so here is what to check.
Chat history arrays are a log, not memory. This walks through the LLM memory layer I build instead: DSPy signatures for extracting atomic facts, QDrant for per-user vector storage, and a maintenance agent that decides when an old fact gets updated or deleted.
The February 4, 2026 dev chat put client-side media on the road to WordPress 7.0: libvips compiled to WASM, running in a worker thread, with image resizing done in the visitor’s browser instead of on your server.
The WP AI Client merge proposal would put a provider-agnostic AI API in WordPress 7.0: one PHP interface, a fluent prompt builder, WP_Error returns, and no outbound calls until a plugin configures a provider.
The Core AI team put out a Call for Testing for the AI Experiments plugin. Here is what is in it: MCP server support, markdown feeds, extra providers and AI request logging, plus the $400 API bill that convinced me logging is the part you cannot skip.