ML.

All Posts

What Does Active Record Build on Every Request? Measured the Same Way as Sequelize and GORM

The last post concluded that Ruby is not slow and that most of a Rails request is Active Record. This one compares what Active Record does per request with Sequelize and GORM, by reading the source and measuring. Most of the cost comes from a has_and_belongs_to_many preload that turns every join row into a full record, and there is a way to cut it sharply while keeping the same SQL.

Archify dissected: what changes when the agent writes an IR instead of drawing the diagram?

Archify has the agent write a typed JSON IR and lets a deterministic compiler turn it into a self-contained HTML artifact. I read the repository end to end and built four diagrams with it, watching what the validator refuses, why deliver, visual-check, and human review are kept apart, and what changes when this blog’s own mermaid is ported over.

DeepSeek Harness Hands-On: Dumping the Boot Tree and Swapping Rows With Patches

I booted DeepSeek Harness with a single npx command and no API key, dumped its 145-row boot tree with --dump-config, and edited the patch layer by hand. The web profile ships with every model-facing tool switched off, and the reason turns out to be interesting. I also walked straight into the trap where patching a row config silently kills a CLI flag.

WebMCP Explained: What Changes in Browser Automation When a Web Page Hands Tools Directly to an AI Agent?

WebMCP is a W3C Community Group proposal in which a web page registers JavaScript functions and HTML forms as "tools" on document.modelContext, and the browser mediates those tools to the user's agent. This article lays out the imperative and declarative APIs and the boundaries the browser guarantees, straight from the spec, then calls real tools with Chrome 152 and agent-browser 0.36 to see how it differs from accessibility-tree automation.