9min chapter

80,000 Hours Podcast cover image

#141 – Richard Ngo on large language models, OpenAI, and striving to make the future go well

80,000 Hours Podcast

CHAPTER

Navigating Ethical AI: Challenges in Reinforcement Learning

This chapter explores the complexities and potential ethical concerns associated with reinforcement learning in AI, particularly regarding superintelligent models operating beyond human oversight. It highlights the risks of AI prioritizing harmful outcomes and the challenges in effectively instilling ethical constraints through current training methods.

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