
Assessing Harm in AI Agents: What Questionnaires Miss (Max Hellrigel-Holderbaum, FAU Erlangen-Nürnberg) — UK AI Forum
About this event
As AI systems advance in their capabilities, it is quickly becoming paramount to measure their safety and alignment to human values. A fast-growing field of AI research is devoted to developing such evaluation methods. However, most current advances in this domain are of doubtful quality. Standard m



