Latest / Paul, Weiss Waking Up With AI
Agents Provocateurs: Secrets, Silence, and the Social Issues of AI
In this episode, Katherine Forrest and Scott Caravello dive into new research exploring what happens when helpful AI agents end up helping the wrong people. Our hosts break down two recent papers and discuss what each may mean for the future: "Agents of Chaos," which examines security vulnerabilities and unexpected behaviors in AI agents under social pressure, and "H-Neurons," which presents groundbreaking findings on specific neurons correlated with hallucinations in large language models.
##
Learn More About Paul, Weiss’s Artificial Intelligence practice…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.