17min chapter

AXRP - the AI X-risk Research Podcast cover image

38.5 - Adrià Garriga-Alonso on Detecting AI Scheming

AXRP - the AI X-risk Research Podcast

CHAPTER

Exploring Decision-Making in Neural Networks

This chapter examines the performance of recurrent neural networks in game-like environments and how additional thinking time impacts their problem-solving capabilities. It explores the development of intrinsic meta-strategies within the networks, particularly regarding pacing and resource management in decision-making. The discussion also highlights the complexities of planning behavior in AI, with a focus on goal-directed actions and the cognitive demands involved in executing strategies.

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