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. Design and build data pipelines that aggregate risk, control, and asset information from across Anthropic's technology stack, solving hard integration problems like disparate schemas, inconsistent data quality, and unified views of posture.