Roman Yampolskiy - The Blacker the Box, the Bigger the Risk (Early Experience of AGI, Episode 3)

Listen to this episode from The Trajectory on Spotify. This is an interview with Roman V. Yampolskiy, a computer scientist at the University of Louisville and a leading voice in AI safety. Everyone has heard Roman's p(doom) arguments, that isn't the focus of our interview. We instead talk about Roman's "untestability" hypothesis, and the fact that there maybe untold, human-incomprehensible powers already in current LLMs. He discusses how such powers might emerge, and when and how a "treacherous turn" might happen.This is the Third episode in our new “Early Experience of AGI” series - where we explore the early impacts of AGI on our work and personal lives.Listen to this episode on The Trajectory Podcast: https://podcasts.apple.com/us/podcast/the-trajectory/id1739255954Watch the full episode on YouTube: https://youtu.be/Jycmc_yIkU0See the full article from this episode: https://danfaggella.com/yampolskiy1...There are three main questions we cover here on the Trajectory:1. Who are the power players in AGI and what are their incentives?2. What kind of posthuman future are we moving towards, or should we be moving towards?3. What should we do about it?If this sounds like it's up your alley, then be sure to stick around and connect:-- Blog: danfaggella.com/trajectory-- X: x.com/danfaggella-- LinkedIn: linkedin.com/in/danfaggella-- Newsletter: bit.ly/TrajectoryTw-- YouTube: https://www.youtube.com/@trajectoryai