Artwork

Content provided by Kanjun Qiu. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Kanjun Qiu or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

Episode 12: Jacob Steinhardt, UC Berkeley, on machine learning safety, alignment and measurement

59:39
 
Share
 

Manage episode 295254144 series 2906499
Content provided by Kanjun Qiu. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Kanjun Qiu or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Jacob Steinhardt (Google Scholar) (Website) is an assistant professor at UC Berkeley. His main research interest is in designing machine learning systems that are reliable and aligned with human values. Some of his specific research directions include robustness, rewards specification and reward hacking, as well as scalable alignment.

Highlights:

πŸ“œβ€œTest accuracy is a very limited metric.”

πŸ‘¨β€πŸ‘©β€πŸ‘§β€πŸ‘¦β€œYou might not be able to get lots of feedback on human values.”

πŸ“Šβ€œI’m interested in measuring the progress in AI capabilities.”

  continue reading

36 episodes

Artwork
iconShare
 
Manage episode 295254144 series 2906499
Content provided by Kanjun Qiu. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Kanjun Qiu or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Jacob Steinhardt (Google Scholar) (Website) is an assistant professor at UC Berkeley. His main research interest is in designing machine learning systems that are reliable and aligned with human values. Some of his specific research directions include robustness, rewards specification and reward hacking, as well as scalable alignment.

Highlights:

πŸ“œβ€œTest accuracy is a very limited metric.”

πŸ‘¨β€πŸ‘©β€πŸ‘§β€πŸ‘¦β€œYou might not be able to get lots of feedback on human values.”

πŸ“Šβ€œI’m interested in measuring the progress in AI capabilities.”

  continue reading

36 episodes

All episodes

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide