Intro to AI Security with Dr Waku

Intro to AI Security with Dr Waku

Welcome to the third episode of the ControlAI Podcast, hosted by Max Winga [https://open.substack.com/users/231071383-max-winga?utm_source=mentions]!  In this episode, Max sits down with AI research scientist and YouTuber Dr Waku [https://www.youtube.com/@DrWaku] to explore AI security challenges. They discuss the risks of jailbreaking, how LLMs' training methods create inherent vulnerabilities, and the growing threat posed by well-funded and highly-focused bad actors with access to current AI models.

Ex-OpenAI Researcher Warns AI Companies Will Lose Control of AI | ControlAI Podcast #2 w/ Steven Adler

Welcome to the second edition of the ControlAI Podcast, hosted by Max Winga [https://open.substack.com/users/231071383-max-winga?utm_source=mentions]! In this episode Max sits down with Steven Adler [https://stevenadler.substack.com], former OpenAI safety researcher who led their dangerous capabilities evaluations and our own Andrea Miotti [https://open.substack.com/users/80637210-andrea-miotti?utm_source=mentions]. Their conversation pulls back the curtain on what's really happening inside the world's top AI company, alarming behaviour across current AI models, the shocking state of internal safety research, and much more.

Avoiding Extinction with Andrea Miotti and Connor Leahy

The risk of extinction from Artificial Intelligence grows alarmingly quickly as AI companies race to build system vastly smarter than humans. What solutions are there for this unprecedented threat? Host Max Winga is joined by ControlAI's Director Andrea Miotti and Conjecture's CEO Connor Leahy to discuss.