Go offline with the Player FM app!
Hansohl Kim: What Is Reinforcement Learning?
Manage episode 506797982 series 1017289
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
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
Manage episode 506797982 series 1017289
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
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
×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.