Hansohl Kim: What Is Reinforcement Learning?

About this episode

Hansohl Kim discusses reinforcement learning and AI safety, focusing on the challenges of alignment and designing trustworthy AI systems.

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 ...

People in this episode

Host: Amy Jo Kim

Guest: Hansohl Kim

Topics covered

• reinforcement learning
• AI safety
• alignment challenges
• AI systems design
• trust in AI

Keywords

• reinforcement learning
• AI safety
• alignment
• guardrails
• trustworthy AI

Mentioned in this episode

Organizations: Anthropic

Products: Claude

More episodes of Getting2Alpha

• Humans Tell The Best Stories · May 11, 2026 · 24 min
• Chelsea Howe: AI, Game Jams, & the Future of Games · December 4, 2025 · 29 min
• Lisha Li: Democratizing Game Creation Through AI · November 4, 2025 · 30 min
• Hugo Alves: Synthetic Users · August 28, 2025 · 39 min
• Amy Bucher: Designing Behavioral Nudges · August 4, 2025 · 29 min
• Nate Bosshard: Algorithmic Immunity · June 5, 2025 · 44 min