5min chapter

The Logan Bartlett Show cover image

EP 63: Eliezer Yudkowsky (AI Safety Expert) Explains How AI Could Destroy Humanity

The Logan Bartlett Show

CHAPTER

The Multiple Reflective Stable Fixed Points of Optimization

There's multiple reflectively stable fixed points of optimization. If you have something that only wants to make tiny molecular spirals out of all of or like it has some much more it ended up with some much more complicated and messy set of desires. And so your current preferences current utility function ends up less satisfied if you execute the self modification. There can be minds more complicated than that but they're being complicated even if they're in some sense unstable doesn't mean that what they end up falling into as a stable attractor is nice to all sentient life.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode