6 posts tagged with "AI"

Clarke's third law says a sufficiently advanced technology is indistinguishable from magic. Anthropology has a working definition of magic that goes further than that line, and the definition fits how millions of people use AI models in 2026. A person appeals to a force they cannot examine, in words they choose carefully, for personal gain, and the outcome sometimes ends badly for them or the people around them. That shape shows up across three areas: what magic actually is, why societies eventually banned it, and what separates someone who can only cast spells from someone who understands the mechanism.

Kiro's context usage meter read 30% while Claude Opus 5 told me in the same chat that it had no room left to work with. Kiro measured the real usage. The model estimated its own remaining context, and the estimate was wrong by a wide margin. The behavior has a name, "context anxiety", and both a production write-up and a peer-reviewed paper describe it.

The Statement Processor reads PDF bank and credit card statements, extracts every transaction, and groups them by vendor. It's finished and on GitHub under an MIT license. Building it surfaced a problem worth writing down: even on a clean, digitally-generated PDF straight from the bank, the table extraction sometimes dropped a row, usually the last one in a transaction table. A sum check that compares the extracted transactions against the total the statement already prints on itself is what made the output trustworthy.

Docling with the EasyOCR engine extracted the Cyrillic text and page structure from a scanned Soviet cookbook, but it dropped text where the pages curved away from the camera. That data loss makes this configuration insufficient on its own for the soviet.recipes project. I tested four sample pages configured for Russian and English, using Kiro.dev to write the script.

Phase 1 of the soviet.recipes project is done: every page of the cookbook is now captured as a set of 224 high-resolution DSLR images. Now I'm planning how to turn those images into machine-readable text.

When a prehistoric artist pressed a pigment-covered hand to a cave wall and blew color around it, something remarkable happened. The resulting outline was a declaration of presence and also an admission of absence. The handprint was not a hand. It was a trace of someone who lived, breathed, hoped, feared, hunted, loved, and eventually vanished. This gap between representation and reality has always shaped how humans express themselves.

René Magritte (1898–1967) — Image taken from "Approaches to Modernism". Fair use (over-50)

Magritte reminded us of the same truth much later with a pipe that "was not a pipe." His painting has become a classic example of a meta-message, a communication about communication itself. Like Alfred Korzybski's insight that "the word is not the thing" and "the map is not the territory," or Denis Diderot's literary experiment This Is Not a Story, Magritte's work highlights the fundamental gap between symbols and what they represent.

We intuitively recognize that no medium can ever contain the living substance of the person who created it. This very blog post is its own meta-message, acknowledging that these words about representation are themselves only representations, and that this post about the impossibility of digital presence is itself an attempt at digital presence.

This tension sits at the heart of every form of self expression. The medium gestures toward the self but never equals it. And yet we continue to endeavor, knowing the attempt will always fall short.