Talks

Regulating Technology

A technology survives as long as it serves a solution in a better way than the problems it adds. Digitization has evolved from interesting to crucial in only a few decades. Artificial Intelligence shall experience an even faster adoption and challenges us to form opinions about things we didn’t grow up with and don’t always understand so well. That accompanies our move towards new regulation with panic, a rush for easy answers and inadvertence to complexities at hand.

By — Dr. Óscar Nájera
— Nürnberg Convention Center

Sleeper agents: training deceptive LLMs that persist through safety training

From political candidates to job-seekers, humans under selection pressure often try to gain opportunities by hiding their true motivations. They present themselves as more aligned with the expectations of their audience than they actually are. If an AI system learned such a deceptive strategy, could we detect it and remove it using current safety training techniques?

By — Dr. Óscar Nájera
— ZOLLHOF - Tech Incubator | AI