News
Rerankers Aren't Magic Either: When the Cross-Encoder Layer Is Worth the Cost
3+ hour, 12+ min ago (1212+ words) Enterprise Document Intelligence [Vol. 1 #2bis] Why stacking a reranker on top of weak retrieval doesn't save it, what cross-encoders actually fix vs what they don't, and where the editorial position of the series lands. Same setup as the embeddings article. Two…...
Proxy-Pointer RAG: Eliminating Wasteful Entity & Relations Extraction in Knowledge Graphs
5+ hour, 12+ min ago (908+ words) In my previous article on Solving Entity and Relationship Sprawl in Knowledge Graphs, I discussed how Proxy-Pointer architecture can optimize searching for right entities and relations. That, however, is only the second part of a larger problem in graph ingestion....
Meta-Cognitive Regulation Might Be the Most Important AI Skill Nobody Is Talking About
1+ day, 1+ hour ago (1187+ words) As AI gets smarter, the real differentiator may be how well humans regulate their own thinking. We all have been leaning into the world of generative AI adoption for almost the past three years now. We've spent the last three…...
Embeddings Aren't Magic: The Predictable Failure Modes of RAG Retrieval
1+ day, 3+ hour ago (1732+ words) Enterprise Document Intelligence [Vol. 1 #2] Why the same vector search that handles synonyms and paraphrase silently fails on negation, exact identifiers, and your company's acronyms, and what to use when it does. Two scenes, both familiar. Scene 1: A RAG system over…...
Qdrant Turbo Quant Explained: Is Turbo Quant the Silver Bullet?
1+ day, 5+ hour ago (1696+ words) Most engineers see quantization as shrinking vectors. Turbo Quant asks a harder question: can you shrink them without breaking their geometry? In early May of 2026, Qdrant released Turbo Quant, a new quantization method. And they claimed that "Turbo Quant can…...
Baseline Enterprise RAG, From PDF to Highlighted Answer
1+ day, 22+ hour ago (1795+ words) Enterprise Document Intelligence [Vol. 1 #1] The smallest version of RAG that actually works, on a real PDF, with grounded answers and the source lines highlighted. The fastest way to understand what RAG is is to build the smallest version that actually…...
RAG Is Burning Money " I Built a Cost Control Layer to Fix It
2+ day, 1+ hour ago (1743+ words) Most RAG systems optimize for relevance, not cost. I built a production-ready cost control layer combining semantic caching, query routing, and budget enforcement that reduces LLM costs by 85% without sacrificing answer quality. This article shows a full working implementation in…...
Five Questions About Chronos-2, the Time Series Foundation Model
2+ day, 6+ hour ago (1765+ words) Foundation models are now mainstream. We first saw them in language, then vision, and now also in video and speech. The recipe by now is familiar: first, pretrain a big neural net on large enough data, then apply the model…...
Diffu Judge-AV: A Diffusion-Inspired Framework for Calibrated AV Video Evaluation
3+ day, 6+ hour ago (1807+ words) There is a particular kind of result that looks impressive until you ask the wrong second question. In this project, that result was a Pearson correlation of 0. 753 from a text-only Claude judge grading autonomous-driving visual-QA answers. At first glance, that…...
Emo Net: Speaker-Aware Transformers for Emotion Recognition " and What I'd Build Differently in 2026
3+ day, 1+ hour ago (1449+ words) A retrospective on my MS thesis, the leaderboard it placed on, and the LLM shift that has reshaped the field since. In March 2024, I submitted my MS thesis on Emotion Recognition in Conversation (ERC). The model, Emo Net, achieved a…...