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.
-
Policy Optimization Algorithms for Alignment
How PPO, GRPO, and DPO guide language models toward more helpful and safer responses.
-
Gaming the System: Understanding Reward Hacking in LLM Training
How language models exploit training rewards, and what we can do about it.
-
Betting on Your Attention: Multi-Armed Bandits for Recommendation Systems
How recommendation systems use multi-armed bandits to balance familiar favorites with new discoveries.