Ep. 136: The case for taking AI Safety seriously | Rob Miles

Through a series of popular explainer videos, Rob has become one of the most prominent voices in the AI safety community, exploring topics like cryptography, recursive self-improvement, and meso-alignment with hundreds of thousands of fans. In this interview, we spend nearly two hours getting into the weeds on how powerful AI systems might be dangerous, and the technical solutions which can mitigate that threat. Check out Rob's work: https://www.youtube.com/@RobertMilesAI Learn more about your ad choices. Visit megaphone.fm/adchoices