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. Experience setting the research strategy for a product or product area, with a track record of research that changed direction at the strategy level, not just the feature level, in direct partnership with product or organization leaders.