Posts

• May 19, 2025

  Policy Optimization Algorithms for Alignment

• May 13, 2025

  Gaming the System: Understanding Reward Hacking in Language‑Model Training

• Mar 24, 2025

  Multi-Armed Bandit Algorithms for Recommendation Systems

• Mar 10, 2025

  Resilient Verses: Exploring the Enduring Power of "Invictus"

subscribe via RSS