Anthropic Alignment Blog · December 2025 Open Source Replication of the Auditing Game Model Organism Authors: Abhay Sheshadri, Me, Kei Nishimura-Gasparian, Sam Marks, Rowan Wang, Johannes Treutlein Tl;dr: Replicated Marks et al. using Llama 3.3 70B ← Go Back Read →