Search a title or topic

Over 20 million podcasts, powered by 

Player FM logo
Artwork

Content provided by Amy Jo Kim. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Amy Jo Kim 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://podcastplayer.com/legal.
Player FM - Podcast App
Go offline with the Player FM app!

Hansohl Kim: What Is Reinforcement Learning?

40:01
 
Share
 

Manage episode 506797982 series 1017289
Content provided by Amy Jo Kim. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Amy Jo Kim 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://podcastplayer.com/legal.

Hansohl Kim is an engineer at Anthropic, where he focuses on reinforcement learning & AI safety for models like Claude. With experience spanning computer science, biotech, & machine learning, he brings a unique perspective to the fast-changing world of artificial intelligence.

Listen as Hansohl unpacks the challenges of alignment, the importance of guardrails, & what it takes to design AI systems we can truly trust.

RELATED LINKS:
🌐 Anthropic – https://www.anthropic.com
💼 Hansohl Kim on LinkedIn – linkedin.com/in/hansohl

  continue reading

Chapters

1. Hansohl Kim: What Is Reinforcement Learning? (00:00:00)

2. Journey into AI and Anthropic (00:01:18)

3. Moving from Computation to Reinforcement Learning at Anthropic (00:03:43)

4. Understanding Reinforcement Learning (00:04:54)

5. Practical Implementation of Reinforcement Learning (00:10:00)

6. Challenges and Guardrails in AI (00:14:11)

7. Reinforcement learning is a very blunt approach (00:17:36)

8. Better to give lots of feedback (00:19:16)

9. Better to give lots of feedback (00:21:10)

10. Behaviorism and AI Motivation (00:22:10)

11. AI Motivation and Internal Processes (00:23:12)

12. Beyond Reinforcement Learning (00:29:22)

13. The Rise of AI Agents and Multi-Agent Systems (00:32:04)

14. Conclusion and Final Thoughts (00:37:16)

104 episodes

Artwork
iconShare
 
Manage episode 506797982 series 1017289
Content provided by Amy Jo Kim. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Amy Jo Kim 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://podcastplayer.com/legal.

Hansohl Kim is an engineer at Anthropic, where he focuses on reinforcement learning & AI safety for models like Claude. With experience spanning computer science, biotech, & machine learning, he brings a unique perspective to the fast-changing world of artificial intelligence.

Listen as Hansohl unpacks the challenges of alignment, the importance of guardrails, & what it takes to design AI systems we can truly trust.

RELATED LINKS:
🌐 Anthropic – https://www.anthropic.com
💼 Hansohl Kim on LinkedIn – linkedin.com/in/hansohl

  continue reading

Chapters

1. Hansohl Kim: What Is Reinforcement Learning? (00:00:00)

2. Journey into AI and Anthropic (00:01:18)

3. Moving from Computation to Reinforcement Learning at Anthropic (00:03:43)

4. Understanding Reinforcement Learning (00:04:54)

5. Practical Implementation of Reinforcement Learning (00:10:00)

6. Challenges and Guardrails in AI (00:14:11)

7. Reinforcement learning is a very blunt approach (00:17:36)

8. Better to give lots of feedback (00:19:16)

9. Better to give lots of feedback (00:21:10)

10. Behaviorism and AI Motivation (00:22:10)

11. AI Motivation and Internal Processes (00:23:12)

12. Beyond Reinforcement Learning (00:29:22)

13. The Rise of AI Agents and Multi-Agent Systems (00:32:04)

14. Conclusion and Final Thoughts (00:37:16)

104 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.

 

Copyright 2025 | Privacy Policy | Terms of Service | | Copyright
Listen to this show while you explore
Play