In this electrifying episode of AI Ignited, host Elif Baser and researcher Ahmet Batu Yılmaz unpack Humanity’s Last Exam—a groundbreaking benchmark featured in The New York Times that challenges the world’s most powerful AI systems on expert-level reasoning, science, philosophy, and more.With insights from AI leaders like Stuart Russell, Yoshua Bengio, and Dan Hendrycks, we explore how models like GPT-4, Gemini, and Claude fare against this new test—and what it means for trust, safety, and the future of intelligence.Is AI reaching a point where we can no longer predict—or control—its answers? Tune in and find out.

Ver todos los episodios