The Hard Problem of Controlling Powerful AI Systems - Computerphile

By Computerphile

Community Score: 50% | 55.1K views | 5mo

0 community ratings: null thumbs up, null thumbs down

As AI systems become more capable, rule-based safeguards, hard-coded restrictions, and simple alignment strategies start to break down. Buck Shlegeris talks about some tactics we might use as detailed in a recent paper. The referenced paper: https://arxiv.org/abs/2504.10374 Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: https://jane-st.co/computerphile This video was filmed and edited by Sean Riley. Computerphile is a sister project to Brady Haran's Numberphile. More at https://www.bradyharanblog.com

Tags: computers, computerphile, computer, science

More from Computerphile

  • Digital Signal Processing With Audio Data - Computerphile — Score: 50%
  • Network Basics - Transport Layer and User Datagram Protocol Explained - Computerphile — Score: 50%
  • Generating 3D Models with Diffusion - Computerphile — Score: 50%
  • Implementing Passkeys in Practice - Computerphile — Score: 50%
  • LLMs and Newcomb's Problem - Computerphile — Score: 50%
  • Do Computer Scientists Prefer Tea or Coffee? (Microphone Sound Check Question 2025) - Computerphile — Score: 50%