Click any tag below to further narrow down your results
Links
The article examines why translating natural language into SQL for live data warehouses remains a tough problem. It traces the rise of ad-hoc queries in 1990s‐era historical data stores and shows how schema complexity and performance needs outpace current text-to-SQL systems.
Karpathy outlines three software eras: human-written code, trained neural weights, and now natural language prompts. He claims LLMs treat English as code, making traditional coding steps optional. The linked talk will explain why this shift matters in 40 minutes.