§ evals · storyline
Microsoft releases ASSERT framework for AI behavior testing
Microsoft releases ASSERT, an open-source framework that lets developers generate and run AI behaviour tests using natural-language descriptions.
Ram Iyer / TechCrunch: Microsoft releases ASSERT, an open-source framework that lets developers generate and run AI behavior tests using natural-language descriptions — AI researchers and labs have advanced by leaps and bounds in evaluating AI models for everything from safety and compliance to sycophancy and alignment.
§ sources1 publication · timeline below