-
👁 Image Parse Scanned PDFs for RAG with EasyOCR: Free OCR Gives You Words, Not a Document
Large Language ModelsEnterprise Document Intelligence [Vol.1 #5quinquies] – Same 1974 scanned PDF, two engines. EasyOCR recovers text.…
15 min read -
👁 Image GPU-Resident Top-K for Agentic RAG: I Built a CUDA Kernel So My Retrieval Step Would Stop Bouncing Off the GPU
Agentic AIThe PCIe transfer latency is silently bottlenecking your agentic inference. Here is how building a…
31 min read
Latest
-
👁 Image Structured Outputs with LLMs: JSON Mode, Function Calling, and When to Use Each
Large Language ModelsGetting reliable, readable responses out of your LLM, and knowing which tool to reach for
11 min read -
👁 Image Learn about the upsides and downsides of Claude Fable 5
9 min read -
👁 Image For decades, the existence of the hydrophobic core, a region in the 3D structure of…
12 min read -
👁 Image Dispatching the Parsed RAG Question: Chunk Strategy, Model Tier, Activations, Audit
Large Language ModelsEnterprise Document Intelligence [Vol.1 #6c] – The decisions the parser makes on top of the…
28 min read -
👁 Image A hands-on guide to setting up image similarity search in Milvus, and why visual replication…
8 min read -
👁 Image How unit economics should set your classification cutoff, and why they rarely do.
15 min read -
👁 Image The Secret to Reproducible and Portable Optimization: ORPilot’s Intermediate Representation (IR)
Agentic AIWhy production-level AI optimization modeling agent needs reproducibility and portability, and how IR helps achieve…
15 min read -
👁 Image Most LLM applications need a clear workflow, not an autonomous agent. Here’s how to build…
19 min read -
👁 Image What the Question Parser Extracts from a User String: Keywords, Scope, Shape, Decomposition, Clarification
Large Language ModelsEnterprise Document Intelligence [Vol.1 #6b] – The five field families the parser reads straight from…
31 min read
Editor’s Picks
-
👁 Image Budgets for AI tokens can’t be infinite, no matter how much hyperscalers wish they were
8 min read -
👁 Soccer goal in a desert by sunset. Image generated with Leonardo AI A single model hands you a single answer and no sense of how much it…
11 min read -
👁 Image Let’s practice data science thinking through a probability problem
9 min read -
👁 Photo by Growtika on Unsplash Claude can now write its own harness on the fly, custom-built for the task at…
28 min read -
👁 Image Why “average utilization” lies about how full your GPUs really are
13 min read -
👁 Image A structured methodology for comparing candidate models, testing stability, and selecting a robust final score
18 min read -
👁 Image A quick guide to separating Physical AI from world models, embodied AI, physics AI, and…
9 min read -
👁 Image This is how LLMs are used today to increase precision in recommendation systems
10 min read
The Variable Newsletter
Deep Dives
-
👁 Image The System Always Knows: Why Local Efficiency and System Performance Are Not the Same Problem
Data ScienceHow local optimization in last‑mile delivery can quietly break the system
15 min read -
👁 Image A systems-level deep dive into the hidden microarchitectural costs of Kubernetes GPU time-slicing, and what…
22 min read -
👁 Image Increasing context size in RAG systems doesn’t improve accuracy for aggregation tasks—it makes errors harder…
15 min read -
👁 Image Why Decade-Old Residual Connections Still Power All of AI (And Why That’s a Problem)
Large Language ModelsFor nearly a decade, this part of neural networks barely changed. DeepSeek is trying to…
16 min read -
👁 Image Enterprise Document Intelligence [Vol.1 #5B] – One PDF in, a relational set of DataFrames out:…
29 min read -
👁 David vs Goliath An in-depth performance test comparing Nucs and Choco
22 min read
