THE REDACTED ASSISTANT (2025–2026)

A prompt, one of five writing styles, and a density slider. The model generates a passage and returns it as a JSON array in which every word and punctuation token carries a redaction rank: -1 for tokens that stay visible, and positive integers ordering the rest by semantic importance, lower being more significant. The interface then masks words and lets the reader click to reveal them, type replacements into the gaps, or export either a fill-in worksheet or a complete answer key as plain text.

Ranking happens once, at generation. The density slider works locally: it filters to ranked tokens, computes how many to hide from the density value, sorts the ranks, takes the rank at that position as a threshold, and masks everything at or below it, so density changes are instantaneous.

Each of the five styles has its own system instruction built on named references — Hegel, Levinas and Schelling for the philosophical mode, the CCRU’s theory-fictions for the hyperstitious one. Uploaded .txt or .md files can seed the prompt directly. Exports are generated client-side as blobs with no server round-trip.

In production, generation calls proxy through a rate-limited Netlify function that holds the API key. Sessions live in browser localStorage, scoped to each visitor. A Tauri wrapper builds the same frontend as a macOS desktop app.