Skip to main content
MICHIEL HORSTMAN
← Back home

RESEARCH / INDEX

Questions I could only answer in code.

Model behaviour, privacy, and the tooling that falls out of both. Each entry links to the work itself: a result with its numbers, a repository with its code, or project notes with what I got wrong.

Editing a small model's existing weights to add physics and depth abilities and repair thinking-mode looping, with full results, method and limits.

READ THE RESULT

Everything else

  • STUDY2025-09

    Blasphemous

    Tooling for studying how transformer models represent refusal, and what happens when projection or LoRA interventions are measured against a fixed evaluation.

  • ZKYC zero-knowledge identity banner
    STUDY2026

    ZKYC

    Zero-knowledge identity: a Circom circuit and browser-side Groth16 proofs combined with a vision model that checks document authenticity.

  • Code Cartographer banner: codebase maps for AI agents
    TOOL2026-09

    Code Cartographer

    A Go CLI that maps a codebase for agents: 22 languages, symbol and source search, dependency impact, and token-budgeted context.

  • Open Vision video-analysis project banner
    TOOL2026-05

    Open Vision

    A local-first video-analysis CLI that returns timestamped visual and audio evidence an agent can use, instead of a prose summary.

Where the work travelled

  • Apr 2025

    My analysis of GPT-4o's behaviour was cited as a source in a thread that reached 32M views; Elon Musk replied “Yikes” inside it.

Surface. Thanks for diving.

Shark model by alextkd2003, CC BY, converted to ASCII.