DeepEval added a mode where Jev, not a generative LLM, decides the score. What that buys you, what the real benchmark numbers show and where it runs out of road.
A CLI tool that asks a decision model which files are relevant instead of pattern-matching for them. The benchmark numbers come with a real caveat worth reading before you trust them.
OpenAI's Decisions API returns predicates, choices and scores instead of free text. What's confirmed about it, how it differs from Jev under the hood and what I'd do about it in a production system.
TypeSafe AI's Jev returns typed answers with calibrated probabilities to a fixed set of questions and generates no tokens. How it works and where I'd put it in a production system.
Graph modeling choices that decide whether a Neo4j lineage graph can answer "where did this value come from" or only looks like it can.
A field guide to the column type, index and distance mistakes that catch almost everyone new to PostGIS.
Why my thesis evaluation pipeline scored every run with both a deterministic benchmark and an LLM judge. The disagreements between them turned out to be the useful part.
In my thesis work the model only routes questions to the right data partition and pushes predicates down to PostGIS and Neo4j. Inference token cost dropped 3x and routing-index quality ended up deciding answer accuracy.
Papyrus runs the embedding model, the vector search and the reranker entirely in your browser. Here's how I made a million-document index fit on consumer hardware.
A field guide to two PySpark performance problems that hide behind healthy-looking averages. Covers what Databricks now fixes for you before you reach for salting.
Memvid started as a joke about hiding AI memory inside MP4 video files. The serious version that replaced it drops the video entirely. It's worth explaining why.
A field guide to the failure modes that don't show up in tutorials and how to systematically debug them.
MTEB scores won't help you here. How I choose embeddings when the data has structure.
Everyone asks this question. Most of the answers online are wrong or at least incomplete.
How to go from messy documents to structured, queryable knowledge without a PhD in NLP.