Full abstract coming soon.
Emmanuel Ameisen currently works at Anthropic where he finetunes LLMs like Claude to be more helpful, harmless and honest. Before joining Anthropic, he was at Stripe, where he made foundational improvements to core fraud models and led efforts to automate the training and deployment of ML models. Previously, he was Head of AI at Insight, where he helped hundreds of Fellows build applied ML projects. Before that, he worked as a Data Scientist at Zipcar and LocalMotion building data products.