Description
Eugene Yan, a Member of Technical Staff at Anthropic, writes about building AI-powered products: recommendation systems, large language models, evaluation, engineering practices and leadership. His posts are practical and grounded in shipping real systems, with recent pieces on patterns for building cybersecurity evals, using LLMs to secure source code, how to work and compound with AI, and product evals in three simple steps. A strong resource for engineers who need to move LLM features from prototype to a reliable product.
