Speaker: Joaquín González Rodríguez.
Abstract: With the omnipresence of AI in the media, it has become increasingly difficult to separate relevant information from background noise, with predictions ranging from utopian promises to apocalyptic scenarios. Moreover, much of the existing scientific literature on AI ethics, risks, and safety was written before the emergence of current “intelligent” systems. For the adoption of AI in everyday life, trust is essential — but who guarantees that AI systems perform “correctly”? In this talk, I will provide an overview of different approaches to AI ethics, risks, and safety, highlighting the paradox between theoretically-desired and deployed models.