Archive
Everything, newest first. Titles carry the month they were written; this stuff ages fast enough that it matters which world a post was looking at. Grouped by topic instead, on the main page.
September 2026
- A beautiful world, and nobody owns it
- The math behind a beautiful world
- The $11 trillion AI capex mirage
- Hiding in the weights: a blueprint for cryptographic life in LLMs
- The proof is impossible. Refactor. The proof is trivial.
- The green theorem that guards nothing
July 2026
- Mail over git: giving agents an identity and an address
- If you can state it, you can probably prove it
- Turing complete and safe: running untrusted code without a cage
May 2026
- When your safe agent helpfully leaks your API key
- l3m: A Verified Coding Agent
- Reading a library from its manifests
- Manifests as specs: a debug-first design exercise
- Two-eyed tools: pair programming when one of you can’t see
- Who owns this code? Specs, manifests, and clean-room reimplementation in the AI era