80,000 Hours Podcast cover image

#81 - Ben Garfinkel on scrutinising classic AI risk arguments

80,000 Hours Podcast

CHAPTER

Exploring Objections to the Mesa Optimizer Argument

This chapter examines key objections to the Mesa Optimizer argument, highlighting concerns about clarity and robustness. It discusses the potential divergence of AI goals from their intended objectives and the importance of identifying issues early to mitigate risks.

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