Azeem Azhar's Exponential View cover image

The Coming AI Hackers

Azeem Azhar's Exponential View

00:00

The Costs of Not Being Explainable

We've talked a lot about explainability and a i systems on previous episodes of this podcast. And it strikes me that the costs of explainability are tangible ther measurable. But the costs of not being explainable are somehow uncertain. Their sort of optionalities in the and distant future that is like an externality for a future generation to deal with. So it feels that we have a kind of, like a human incentive alignment problem here.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app