-
The idea that makes backpropagation possible.
14 min read -
Using mathematical optimization to solve a pickup-and-delivery problem with time windows.
38 min read
Latest
-
In a world where human time is expensive, learn how to use it only when…
20 min read -
The mean keeps making its usefulness felt in all sorts of situations, often in truly…
45 min read -
A practical reproduction of three retrieval baselines, including the crashes, fixes, and score checks that…
16 min read -
Maximize your efficiency with Claude Code
11 min read -
Building a browser-use agent with OpenAI Agents SDK and Playwright MCP
7 min read -
How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes
Machine LearningArchitecting cost-effective infrastructure by navigating the latency and storage trade-offs of HNSW, SPANN, and DiskANN
11 min read -
I generated a Kármán vortex street without solving a single fluid equation. Here’s how the…
13 min read -
Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet
Large Language ModelsTabular foundation models predict the missing column of any spreadsheet zero-shot, the way an LLM…
24 min read -
Automating the classification and extraction of PII from emails using AWS
14 min read
Editor’s Picks
-
Patience, Optimism, Discipline, Projects, Teams
6 min read -
If you have ever wanted to actually build an LLM inference runtime yourself — pack…
20 min read -
How Much of a Data Science Workflow Can Run on a GPU Today? Part 1: Accelerating Data Preparation
Data EngineeringExploring GPU acceleration with cuDF, cudf.pandas, and the Polars GPU Engine
10 min read -
On the value of building on existing foundations
9 min read -
AI’s energy crisis is reviving an old idea: computing with physics instead of digital logic.…
11 min read -
Why your regression coefficients keep changing, and what geometry has to do with it.
24 min read -
The analytics career I signed up for five years ago doesn’t exist anymore, and honestly,…
6 min read -
How to stop parsing JSON by hand and start trusting your model’s output
10 min read -
My PhD models tried to explain why people engage. My industry models predict who will.…
19 min read
The Variable Newsletter
-
Authors can now benefit from updated earning tiers and a higher article cap
2 min read -
Sorting through the good, bad, and ambiguous aspects of vibe coding
4 min read
Deep Dives
-
Loop Engineering for RAG Generation: An LLM Cascade from a Cheap Local Model Up to a Hosted Flagship
Large Language ModelsEnterprise Document Intelligence [Vol.1 #8quater] – Two angles on the cascade, cost and a validation…
13 min read -
Context Windows Forget What Matters — I Built a Usage-Reinforced Decay Engine for AI Agent Memory
Large Language ModelsMost AI memory systems keep the newest information—not the most important. Here’s how I used…
23 min read -
Detecting Vulnerabilities in Agent Skills with SkillSpector: From Green Checkmark to Real Security Judgment
Agentic AIStatic analysis nailed the malicious skill and over-flagged the useful one. The gap between those…
24 min read -
A reproducible 100-step LoRA fine-tuning run for OpenVLA, with dataset checks, Colab setup, training metrics,…
15 min read -
Let’s discover how neural networks learn, step by step
15 min read -
An AI agent passed every metric in the eval harness I published, then the CFO…
18 min read