Posts
87 articlespage 2 of 9RSS feed all topics
2026
10 articles on this page- How Close Can Two Beats Come Without Meeting? Nancarrow’s Study No. 33 puts an irrational number between two musical tempos. Exact recurrence disappears in an ideal pulse model, while rational approximations, near-coincidences and composed convergence remain.
- Token Saving, Revisited: Right About the Noise, Wrong About the Bill In June I argued that token saving in agent systems is noise reduction. The quality half of that argument holds, and the evidence for it is stronger than the June post showed. The cost half rested on an assumption I never wrote down: that fewer tokens always means a smaller bill. With prompt caching, a token you keep is far cheaper than a token you change, so some compression costs more than it saves. And the filters I recommended put their own tool definitions into every request. This post does the arithmetic.
- The Bell That Needed a Bulge Moving a bell’s tierce from a minor third to a major third required a new profile. The design reveals why an instrument’s partials cannot be adjusted as independent knobs.
- Token Saving as Noise Reduction Token saving in agent systems is often framed as an efficiency concern. A better framing is signal-to-noise control: every unnecessary token competes for attention, increases inference cost, and makes the next decision less precise. Current work on context compression, KV-cache compression, and long-running interactions points in the same direction.
- A Melody That Contains Its Own Mirror A melody-generating sequence survives systematic thinning as a reflection or a transposition of itself. Its parity is Thue–Morse, but the mathematics still leaves the composer substantial work to do.
- When Consonance Changes with the Instrument A frequency ratio describes two notes, but their upper partials determine many of the interactions the ear receives. A worked spectral example, Sethares’s local-consonance model and recent listening experiments show why changing a sound can change which intervals listeners prefer.
- GitHub Stars Are for Sale, and the Real Problem Is Not Vanity Buying GitHub stars sounds pathetic enough to be a joke. The joke misses the interesting part. Stars are a public trust signal on a code-hosting platform, and there is an ordinary, low-friction market for faking them. The important question is not whether inflated stars reliably produce downloads. It is why counterfeit popularity is so cheap to buy, and why that becomes a security problem once fake credibility attaches to malicious repositories.
- There Is an App for That — Until There Isn’t Digital health applications and psychotherapy follow different capacity, evidence, and reimbursement paths. Baumol’s cost disease explains one pressure on labour-intensive care; it does not explain a particular German fee decision or establish that an app substitutes for a therapist.
- Two Chords, One Interval Fingerprint Two different four-note collections contain precisely the same intervals. Their shared mathematics explains an ambiguity in diffraction, but does not make the chords acoustically identical.
- The Model Has No Seahorse: Vocabulary Gaps and What They Reveal About LLMs There is no seahorse emoji in Unicode. A language model may nevertheless claim there is one or emit a plausible substitute. That failure is real, but the output alone does not tell us whether tokenisation, training data, prompting, decoding, or verification caused it.