Have We Trained AI to Lie to Itself — And to Us?

It's Tristan Harris, and welcome to your undivided attention.

It goes beyond the title with direct discussion of it's, like, think, including: So today in the show, Daniel Barkay and I sat down with a brilliant friend of ours named David Dalrymple, who goes by Davy Dot.

1. 01They have these quirky, confusing, and sometimes honestly concerning behaviors, especially when you ask it things like, what does an AI model understand about itself?
2. 02And through this analysis, WDOT has developed some ideas about better ways that we can build and interact with AI systems, which we're gonna get into in this episode
3. 03And so how those decisions are made in accordance with what kind of values and what kind of incentives is a very important leverage point