Writing

Writing

Research notes and conversations.

What we have published. And the podcasts and features we turned up in, because those are easier to lose track of.

ArticleSep 4, 2026· Jingyun Jia· 13 min read

Is Your LLM Actually Looking at the Data? Introducing SleuthBench

Large language models are increasingly being used as data analysts. Give an LLM a CSV and ask, “What is driving customer churn?” It will return a confident answer.

ArticleAug 24, 2026· Joel Webb· 7 min read

What Really Drives Home Prices in King County

King County, Washington is home to Seattle, Bellevue, and some of the most dynamic real estate in the Pacific Northwest. We analyzed 21,613 home sales spanning the full spectrum of the market, from $75,000 starter homes to a $7.7 million waterfront estate, with an average sale price of $540,088.

ArticleAug 17, 2026· Joel Webb· 7 min read

What's Really Aging Inventory On The Lot

A large regional auto group came to us with a question: why is this vehicle still sitting on the lot? I analyzed their full new and used inventory as of May 2026, everything from compact sedans to heavy duty commercial trucks, across five store locations and several brands.

ArticleAug 10, 2026· Joel Webb· 3 min read

Intelligibility Research That Has Stood The Test of Time

Congratulations to Rich Caruana, Yin Lou, Johannes Gehrke, Paul Koch, Marc Sturm, and Noémie Elhadad on receiving the 2026 SIGKDD Test of Time Award for Applied Data Science!

ArticleApr 15, 2026· Aaron Alvarez· 7 min read

Improving Claude Opus from 74% to 100% on three select data science tasks: What Intelligible’s semantic components can do for LLMs

When an LLM reasons about a dataset, it starts from scratch. It writes code to explore the table, fits a quick model or computes correlations, interprets the output, and builds up an understanding of the data's structure, all within a single conversation.