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. Real credibility as a scientist: hands-on experience doing science in academic labs, biotechs, pharma or research institutes, ideally as a user of the kind of tools you''ll help scientists adopt.