Chaos Engineering for Behaviour
Red-teaming a model's behaviour is chaos engineering, and operations already wrote the rules for it.
5 posts with this tag. All tags.
Red-teaming a model's behaviour is chaos engineering, and operations already wrote the rules for it.
A hook can block a word on every reply. Nothing I run can yet catch a model before it folds, only after.
A reading of the Goodhart Labs chess honeypot, three additions to the design, and a dated prediction.
Error budgets, reconciliation loops, separation of duties and recovery over prevention: four operations practices that fit agent work almost line for line.
A language model is a golem made of English. It behaves well only where it can see what its act will cost, and infrastructure is the craft of bringing that cost into view.