MAIA members traveled to DC to showcase critical AI safety concerns at the Congressional Exhibition on Advanced AI, hosted by the Center for AI Policy (CAIP) and supported by Congressman Bill Foster. Our team demonstrated two key risks: automated phone-line attacks capable of mass social engineering, and strategic deception capabilities in advanced AI systems that pose significant alignment challenges. The exhibition provided congressional staffers with hands-on demonstrations of potential AI misuse scenarios.
Stephen Casper
Tony Wang
Eric J. Michaud
Uzay Girit
Kaivu Hariharan
In partnership with AISST
maia-exec@mit.edu
