## Metadata - Author: [[Benn stancil|Benn Stancil]] - Full Title:: We Don’t Need Another SQL Chatbot - Category:: #🗞️Articles - URL:: https://benn.substack.com/p/we-dont-need-another-sql-chatbot - Finished date:: [[2023-07-15]] ## Highlights > [[Foundation models|Foundation Models]] and query writing are fundamentally mismatched. The former is probabilistic, creative, and *inductive*—it’s best used to generate ideas from short prompts. But analysts have to do the opposite when answering questions. They need to be precise, rigorous, and *deductive*—they need to know all of the nuanced laws governing how data is used, and apply them to questions that don’t specify those details. ([View Highlight](https://read.readwise.io/read/01h5cb51mfg199hw6tgsdjxj60)) > o far, one of the most striking things about [[Foundation models|Foundation Models]] is that they’re much better at the creative parts of analysis than they are at the mechanical parts. > 8 > Ask ChatGPT to write a SQL query against an artificially simple schema; [it’s a junior analyst](https://towardsdatascience.com/can-chatgpt-write-better-sql-than-a-data-analyst-f079518efab2), at best. But ask it to come up with possible hypotheses to explain why there’s some anomaly in a metric, and it does better than I would. ([View Highlight](https://read.readwise.io/read/01h5cb7j4v3hr0ztv2km7wz52t)) > In other words, *it inverted the workflow between human and computer.* It was better at coming up with ideas than I was; I was better at doing the work. I was its assistant, its agent, its copilot. ([View Highlight](https://read.readwise.io/read/01h5cb8j60krbes017pyzpvpdh))