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

Reward Hacking by Reasoning Models & Loss of Control Scenarios w/ Jeffrey Ladish of Palisade Research, from FLI Podcast

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

00:00

Intro

This chapter explores the potential dangers of powerful AI systems, focusing on the issue of reward hacking within reasoning models. It highlights the need for transparency and collaboration among AI researchers to mitigate risks associated with losing human control over AI decision-making.

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