AI article
My board never scored an outage as a regression. My evidence couldn't prove it.
Community description: I put a preprint on arXiv this week. It is about forging evidence bundles that my own verifier calls...
Dev.to | Aug 31, 2026 | Erik Hill
Automated excerpt
I run a public drift board that re-tests 17 models against a frozen 35 task suite daily. Three of seventeen models currently carry a disqualified latest run. Yesterday's work taught the verifier to cross-check the floor against two surfaces.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.