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 episod...
All content for The Trajectory is the property of Daniel Faggella and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
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 episod...
Roman Yampolskiy - The Blacker the Box, the Bigger the Risk (Early Experience of AGI, Episode 3)
The Trajectory
1 hour 28 minutes
4 days ago
Roman Yampolskiy - The Blacker the Box, the Bigger the Risk (Early Experience of AGI, Episode 3)
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 episod...
The Trajectory
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 episod...
