"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

Scaling "Thinking": Gemini 2.5 Tech Lead Jack Rae on Reasoning, Long Context, & the Path to AGI

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

00:00

Navigating the Ethics of Reinforcement Learning in AI Reasoning

This chapter explores the challenges of implementing reinforcement learning in reasoning processes, highlighting objectives like readability and avoiding cyclic behaviors. It also discusses the ethical considerations of modifying these objectives and emphasizes the value of expert insights in refining AI models.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app