This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences. Partnering closely with counsel, we provide custom infrastructure and guidance for complex, novel technical matters, empowering teams across the company to continue meeting our legal obligations as we innovate.