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

Exploring Goals in Neural Networks and AI Systems

This chapter examines a recent post on the AI Alignment Forum that emphasizes the need for research into defining internal representations of goals within neural networks. It discusses the uncertainty surrounding AI models like GPT-3 regarding their possession of genuine goals and highlights enthusiasm for connecting theoretical definitions with empirical observations in AI systems.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner