DETECTData & productivity
Jev Analysis of Food.com Reviews
Daniel Vogel@EpicVogel
This project utilized Jev to analyze approximately 1 million historical Food.com reviews, identifying instances of recipe adjustments in both highly critical and highly positive reviews.
Pointed @typesafeai's Jev at ~1M historical food.com reviews and asked it to flag reports of recipe adjustments (substitutions, omissions, quantity changes, method changes, extra ingredients).
It caught them in ~21% of 1-star reviews and ~46% of 5-star reviews. The people who loved dinner were the ones rewriting it🧐
Related builds
Vectorless RAG with Jev
This project introduces a novel approach to Retrieval Augmented Generation (RAG) that replaces traditional embedding methods with a structured, table-of-contents-based navigation system, significantly improving speed and reducing costs by offloading non-generative tasks to Jev.
