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.
Negative-Result
Browse posts by tag
September 15, 2025
KL-Threshold Routing Between LLMs: What Speculative Decoding Already Solved
In 2023 I drafted a paper on routing between a large and small LLM via KL-divergence thresholds. Speculative decoding had already solved the problem more rigorously. Here is the post-mortem.