Tag: verification
-
Can an Open-Weight Model Prove Code Never Crashes?
Anthropic had Claude prove that real programs cannot crash. I tried the same loop at small scale with an open-weight model on two DGX Sparks: GLM-5.3-Flash writing Verus proofs for eight Rust routines. It proved all of them crash-free and found every planted bug, but one fix silenced a crash without fixing it, and the…
-
Grounded Verification and Operational Failure Modes in an Agentic Trading-Card Cataloging Pipeline
A case study describing an agentic pipeline for automated trading-card identification and cataloging, in which claims are grounded in externally verifiable sources and validated by an independent agent. I characterize the system’s design, its operational failure modes, and its per-unit computational cost relative to a hosted commercial API.