April 9, 2026
TD Learning for Exemplar Retrieval: Why It Doesn't Really Work
I tried closing the loop on retrieval-augmented generation with TD learning. A trivial baseline matched the full method. Here's the lesson.
Browse posts by tag
I tried closing the loop on retrieval-augmented generation with TD learning. A trivial baseline matched the full method. Here's the lesson.
On research strategy, what complex networks reveal about how we think through AI conversations, and building infrastructure for the next generation of knowledge tools.
Using GMM clustering to improve retrieval in topically diverse knowledge bases