Domain Specific LLM Inference for AI-SQL

Shreya Shankar on serving LLMs for database-style operations. She is introduced as a researcher in databases and human-AI interaction who built DocETL, an open-source system for processing unstructured data, during her EECS PhD at UC Berkeley, and who joins CMU as an assistant professor in 2027. The talk starts from what AI has become good at: the basic text operations NLP has worked on for decades -- extraction, classification, summarization -- which models have handled passably for a while but only recently handle zero-shot, so nobody has to collect training data first. From there into the inference question that follows once those operations are run at database scale.