Blog

Technical deep-dives on LLMs, RAG, agents, and machine learning from Data For Science.

November 2, 2026

Jev 101

A new class of model

Read more →
October 8, 2026

Local LLM Inference at Scale with vLLM

Continuous batching, prefix caching, and structured outputs: the vLLM features that turn a single local model into a serving engine for thousands of requests.

Read more →
September 20, 2026

The Epidemiology of a Cognitive Virus

What happens when you take "LLM addiction" seriously enough to write down the equations and run simulations

Read more →
September 5, 2026

LLMs Are the New Wikipedia

Every old criticism is new again.

Read more →
August 24, 2026

An MCP Server from Scratch

Interact with a database with the latest version of the MCP Protocol

Read more →
August 11, 2026

Evaluating your Agentic Harnesses

One good demo is a test flight. An eval suite is the flight-test campaign: pass rates, cost, latency, and failure modes.

Read more →
July 27, 2026

Self hosting LLMs with Llama.cpp

Install, download, and serve a small model on Apple Silicon, then read the model file's guts — including the arithmetic for working out whether a given model fits in your RAM.

Read more →
July 14, 2026

Building an Advanced Agentic Harness

From a single pilot to an air campaign: planning, parallelism, memory, verification, and observability for production-shaped agents.

Read more →
June 23, 2026

Build a (small) language model by counting

A 4-gram model on WikiText-103, and the one idea it shares with Claude.

Read more →
May 26, 2026

Building a Basic Agentic Harness

The secret sauce behind Claude Code, Open Clawd, Hermes, etc

Read more →

​

Subscribe to get our latest content by email.
    We won't send you spam. Unsubscribe at any time.