News
Loop Engineering with Adaptive Parsing in Action: Parsing Flat Tables with Azure and Figures with a Vision LLM
10+ hour, 57+ min ago (1750+ words) Enterprise Document Intelligence [Vol.1 #10B] – The LLM as last line of defence, then two real escalations walked end to end: a flat table to Azure, a figure to a vision model 📓 The runnable companion walks both escalations end to end: you…...
Water Cooler Small Talk, Ep. 12: Byzantine Fault Tolerance
12+ hour, 27+ min ago (408+ words) How do you make decisions when you can't trust anyone in the room? Lately, I had a bit of a side quest and spent some time reading about blockchain, fortunately not from a crypto-bro perspective, but rather from genuine curiosity…...
How to Work Effectively with GPT-5.6
3+ day, 9+ hour ago (798+ words) Maximize the latest OpenAI model In this article, I will give my first impressions of the newest OpenAI model, GPT-5.6. The model was released a few days ago, and I’ve gotten the chance to test it extensively since the release…...
Context Engineering Isn’t Enough — A Loop Engineering Experiment With No LLM Inside the Loop
3+ day, 12+ hour ago (1794+ words) The Scope: This isn’t a benchmark pitting agent frameworks against each other, nor does it claim this controller is “smarter.” It claims something narrower and much more defensible: that failure isolation is a real, measurable architectural property. It’s a Pattern,…...
Using Classical ML to Empower AI Agents
3+ day, 10+ hour ago (444+ words) On the value of building on existing foundations When people ask me what I’m doing these days at work, I feel like they are sometimes surprised when I say “building CatBoost classifiers” or “fitting isolation forests”. But this is in…...
One RAG Pipeline, Four Very Different PDFs: Same Four Bricks, Every Answer Typed and Cited
3+ day, 15+ hour ago (1438+ words) Enterprise Document Intelligence [Vol.1 #9B] – One call wires the four upgraded bricks together, run on a paper, a NIST standard, and a report with a broken TOC 📓 The runnable notebook for this article is on GitHub: doc-intel/notebooks-vol1. It runs the…...
Analog AI Is Back, But Can It Survive Its Own Noise?
3+ day, 13+ hour ago (719+ words) Why chipmakers are betting on physics to fix AI's energy problem, and what happens when you actually simulate that noise yourself The numbers back this up. Gartner expects global data center power demand to climb from 104 gigawatts in 2025 to 132 gigawatts…...
Context Engineering for RAG Question Parsing: From a Raw Question to Typed Fields That Steer Retrieval and Generation
4+ day, 10+ hour ago (1529+ words) Enterprise Document Intelligence [Vol.1 #6quater] – Question parsing takes one messy string and writes four typed pieces, each read by a different downstream call When engineers talk about context engineering today, they usually mean retrieving the right context from a document: chunk…...
How to Get the Most Out of Claude Fable 5
4+ day, 12+ hour ago (1121+ words) Maximize your Claude Fable 5 usage Claude Fable 5 was released around a month ago and then, after three days, was pulled from the public because of security concerns. However, it’s now been returned to the Claude subscription, and anyone with the…...
Why Your Betas Explode: The Hidden Geometry of Multicollinearity
4+ day, 13+ hour ago (1781+ words) Why your regression coefficients keep changing, and what geometry has to do with it. Last quarter, I was presenting a marketing mix model to a senior director. The slide showed two beta coefficients side by side: Linear TV at +2.4, Digital…...