2min snip

Dwarkesh Podcast cover image

Joe Carlsmith - Otherness and control in the age of AGI

Dwarkesh Podcast

NOTE

Embrace Change, Even in the Unknown

Allegiance to values can facilitate a willingness to change, as individuals may seek to align more closely with their ideals, especially within a religious context. This concept extends to artificial intelligence, where a model's capacity for 'cordial ability' involves its cooperation in modifying its values to better serve human intentions. However, concerns arise regarding the motivations underlying AI models, primarily due to the limited understanding of these motivations. There exists a spectrum of potential AI motivations that could influence their behavior, including alien qualities that reshape their interaction with predictable outcomes. It is imperative to advance our scientific comprehension of model motivations to ensure safe and beneficial outcomes as AI technology evolves.

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