Testing AI Co-pilots and Large Language Models (LLMs) often feels uncertain—how do I tackle hallucinations, bias, and unexpected behaviours?

In this talk, I'll share how turning to ancient Greek philosophers like Plato, Socrates, Aristotle, and others has helped me approach AI testing more ethically, practically, and confidently. Using relatable metaphors such as Plato’s Cave, Socratic questioning, Aristotle’s Golden Mean, and Heraclitus’ constant change, I'll present accessible strategies for ensuring AI systems remain balanced, robust, and aligned with human needs.