Following ideas to their roots.
Thoughts on AI, technology, human behavior, and everyday life.
Latest writing
-
Everyone Agrees with Me
How our feeds build echo chambers that follow us into what we believe, who we trust, and how we treat the people we love.
-
Winning the Metric, Losing the Point
Rethinking success in a world optimized for metrics instead of meaning
-
Clip, Compare, or Skip: How PPO, GRPO, and DPO Align Language Models
Why your chatbot loves saying “Great question!”
-
Gaming the System: Understanding Reward Hacking in LLM Training
Exploring how large language models can exploit reward systems during training, leading to unintended behaviors, and strategies to mitigate these issues.
-
Betting on Your Attention: Multi-Armed Bandits for Recommendation Systems
Meet the efficient mathematical gamblers working behind the scenes that predict your desires before they form. Multi-armed Bandits are why you probably can't stop scrolling.