Building tools and writing about them honestly.https://thepragmaticquant.com/https://thepragmaticquant.com/when-is-the-swarm-actually-done/https://thepragmaticquant.com/when-is-the-swarm-actually-done/Three services across a network, one dropped task, and a question nobody on the wire can answer: did the work actually get done? A copy-paste demo that exits 0 and prints SUCCESS while the real job dies unseen.Wed, 24 Jun 2026 00:00:00 GMTagentsdistributed-systemsthe problemswarmhttps://thepragmaticquant.com/task-was-destroyed-but-pending/https://thepragmaticquant.com/task-was-destroyed-but-pending/A teardown deadlock I diagnosed in Google's A2A reference SDK — Issue #1101, PR #1105 (313 lines, tests, CI green, open for review) — turned out to be one symptom of a primitive the whole agent ecosystem is missing: a sound signal that an async mesh has actually settled.Wed, 24 Jun 2026 00:00:00 GMTa2aagentsstructured-concurrencythe problemhttps://thepragmaticquant.com/the-first-file-an-agent-reads/https://thepragmaticquant.com/the-first-file-an-agent-reads/Coding agents read your library before they use it, and they start with the code — `__init__.py`, the type hints, the tool schemas — not your docs site. Here is how I made waitbus speak to that reader, and the one piece of documentation I deliberately did not ship.Fri, 19 Jun 2026 00:00:00 GMTwaitbusagentsdocumentationmcphttps://thepragmaticquant.com/coding-agents-cant-hear-each-other/https://thepragmaticquant.com/coding-agents-cant-hear-each-other/Your Claude Code, your Cursor, your tests, your CI — all on one box, none able to hear the others finish or fail. Here's the problem, and the proof: five real LLM agents on one bus, one fails, all wake.Sun, 14 Jun 2026 00:00:00 GMTwaitbusagentsthe problemswarmhttps://thepragmaticquant.com/source-to-subscriber-milliseconds/https://thepragmaticquant.com/source-to-subscriber-milliseconds/The architecture end to end — how an event gets from a source to a waiting agent in single-digit milliseconds, how an agent actually talks to the bus over MCP, and the decisions behind the build with what each one cost.Sun, 14 Jun 2026 00:00:00 GMTwaitbuslatencymcpengineeringhttps://thepragmaticquant.com/why-my-benchmarks-lied/https://thepragmaticquant.com/why-my-benchmarks-lied/Two kinds of trust in one place — the benchmark methodology that makes the speed numbers survive a skeptic (Coordinated Omission, a bimodal p99, costs published as losses), and the supply-chain trail that lets you trust the artifact you install (SLSA provenance, sigstore, reproducible builds, and an honest list of the gaps).Sun, 14 Jun 2026 00:00:00 GMTwaitbusbenchmarkssupply-chainsecurityhttps://thepragmaticquant.com/thirty-one-papers-zero-error-analyses/https://thepragmaticquant.com/thirty-one-papers-zero-error-analyses/A sliding-window inner product updated one product at a time is the streaming similarity engine under motif and anomaly mining — its rounding error grows linearly in stream length, and across thirty-one matrix-profile papers nobody had ever done the forward-error math, or turned the fix into a config knob.Fri, 12 Jun 2026 00:00:00 GMTfloating-pointtime-serieshttps://thepragmaticquant.com/the-accumulator-that-never-moved/https://thepragmaticquant.com/the-accumulator-that-never-moved/An adversarial input where round-to-nearest throws away every increment in the same direction while the true sum climbs — and the coin flip that breaks the adversary's one weapon, measured across 20,000 seeds.Fri, 12 Jun 2026 00:00:00 GMTfloating-pointformal-methodstime-serieshttps://thepragmaticquant.com/the-kernel-nobody-analyzed/https://thepragmaticquant.com/the-kernel-nobody-analyzed/SCAMP and STUMPY accumulate a mean-centred covariance, not the textbook inner product — and the centred case is structurally different floating-point mathematics, not a special case at mu = 0.Fri, 12 Jun 2026 00:00:00 GMTfloating-pointtime-seriesformal-methodsevalshttps://thepragmaticquant.com/green-is-not-evidence/https://thepragmaticquant.com/green-is-not-evidence/An experiment can validate the wrong quantity against the wrong envelope and pass, a self-test canary can fail identically whether the gate works or not, and an audit command can print nothing and exit 0 — three gate designs that read green while checking nothing.Fri, 12 Jun 2026 00:00:00 GMTformal-methodsevalshttps://thepragmaticquant.com/three-axioms-and-one-disclosed-seam/https://thepragmaticquant.com/three-axioms-and-one-disclosed-seam/Four verification tools, one certificate: every machine-checked theorem mechanically reduced to three classical axioms with zero unfinished proofs — and the one place two provers cannot talk to each other, named right in the theorem statements.Fri, 12 Jun 2026 00:00:00 GMTformal-methodsleanfloating-pointevalshttps://thepragmaticquant.com/one-earthquake-pinned-my-bound/https://thepragmaticquant.com/one-earthquake-pinned-my-bound/A seismic stream, a global magnitude bound wrecked by a single mainshock, a windowed bound that heals — and a scoreboard where the headline empirical legs of two papers report zero violations.Fri, 12 Jun 2026 00:00:00 GMTfloating-pointtime-seriesevals