Latest Posts by @cigitalgem
Dear tech press, we will never red team or pen test our way to #AI security. This story is, in that way, a big disservice to #MLsec. Please focus on building security in. Looking at you @TheGuardian https://www.theguardian.com/technology/2026/apr/29/meet-the-ai-jailbreakers-i-see-the-worst-things-humanity-has-produced ...

NEW BIML Bibliography entryhttps://arxiv.org/pdf/2603.28052Meta-Harness: End-to-End Optimization of Model HarnessesLee, Yoonho, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, and Chelsea FinnHarnesses for Agentic AI include perception and memory devices that allow an LLM to externalize and preserve state. This work describes iterating over a set of harnesses and finding better ...
