Acutis / Notes

Notes on proving AI-generated code safe.

The engineering log, in public-ready form. How the verifier works, what our studies actually show, and where a careful reader should push. Written for the person who will try to break it.

Recent writing

Results

F1 = 1.0, and 62.5 points to zero

Two numbers do most of the work when we describe Acutis. Here is exactly how we got each one, exactly what it means, and exactly where a skeptic should push.

2026‑05‑12
Architecture

Zero enumeration: a verifier with no rule list

No function lists, no patterns, no stdlib defaults. The verifier is name-blind, so a framework it has never seen works on day one. Why that is a moat, not a gap.

2026‑07‑20
Framing

Proves safe, not catches bugs

A gate you want to pass, not an alarm you learn to ignore. What changes when security verification runs inside the AI's loop, before code reaches a person.

2026‑07‑21
Evidence

A proof bundle, not a risk score

Each verdict emits a machine-readable record: the property path, the trust assumptions graded by strength, and nothing assumed in silence. The evidence an auditor can read.

2026‑07‑22