The article compares working with large language models (LLMs) to collaborating with human coworkers, emphasizing that both can misinterpret vague instructions. It discusses the importance of clear communication and proper context when interacting with LLMs, suggesting that many frustrations stem from unrealistic expectations of deterministic behavior. Adapting to this probabilistic nature can lead to more effective outcomes.

After two years as CTO at Carta, the author reflects on key lessons learned, including the importance of detail-oriented leadership, refining engineering strategy, and effective communication within teams. They also discuss the challenges and opportunities presented by adopting new technologies like LLMs, as well as insights into managing engineering costs and improving software quality. The author expresses gratitude for their colleagues and the experience gained during their tenure.