Deep dive

Long-form analysis of how something actually works.

8 posts

10 min read

Your Unique Visitor Count Has a One-Month Shelf Life

Umami is MIT-licensed, so the identification path is readable. Where, who and when turn out to be a CDN header, a hash that expires on the 1st, and a bucket quantized to the clock hour.

10 min read

Your Browser Agent Is Not Bound by the Same-Origin Policy

The web's oldest isolation guarantee is a string comparison. Put an agent inside the browser and it becomes a model's ability to resist a prompt injection.

9 min read

Your Agent Re-Sends the Whole Conversation Every Turn

A multi-turn agent replays its entire history on every request. Caching, context editing and compaction each attack a different part of that bill — and one of them, at its defaults, made it worse.

8 min read

Why increase() Returns 27.5

Prometheus reports fractional counts for counters that only ever increment by one. The reason is a specific extrapolation rule, and knowing it tells you exactly when the number can be trusted.

9 min read

Hermes Agent's Learning Loop Is a Counter, a Critic and a Garbage Collector

Hermes Agent says it improves its own skills. In the source, that loop is a tool-call counter, a forked LLM review told to be active, and a curator that archives what nobody uses.

8 min read

Googlebot Is Not Your Browser

Rendering is a separate, queued, stateless stage between crawling and indexing. Almost everything confusing about JavaScript and search comes from ignoring that.

9 min read

Your LLM Is Two Different Machines

Prefill and decode have opposite performance characteristics, and almost everything confusing about LLM latency, cost and context limits falls out of that one split.

10 min read

Your Observability Bill Is a Multiplication Problem

Cardinality does not creep up on you — it multiplies. Here is the arithmetic behind an exploding metrics bill, the four places the multiplication hides, and what actually shrinks it.