Shekhar Tiruwa

Events

• AI Safety Thursdays: Reasoning Models Don't Always Say What They Think 2025-06-12
• AI Safety Thursdays: Tracing the Thoughts of a Large Language Model 2025-06-05
• AI Safety Thursdays: Understanding The Self-Other Overlap Approach 2025-05-22
• AI Safety Thursdays: When Good Rewards Go Bad - Reward Overoptimization in RLHF 2025-05-15