-
Maximize the latest OpenAI model
10 min read -
On the value of building on existing foundations
9 min read
Latest
-
Context Engineering Isn’t Enough — A Loop Engineering Experiment With No LLM Inside the Loop
Large Language ModelsEveryone is talking about loop engineering, but most discussions assume an LLM sits at the…
22 min read -
AI’s energy crisis is reviving an old idea: computing with physics instead of digital logic.…
11 min read -
One RAG Pipeline, Four Very Different PDFs: Same Four Bricks, Every Answer Typed and Cited
Large Language ModelEnterprise Document Intelligence [Vol.1 #9B] – One call wires the four upgraded bricks together, run…
28 min read -
How to define recurring work, give AI the right context, explain what high-quality work looks…
10 min read -
Context Engineering for RAG Question Parsing: From a Raw Question to Typed Fields That Steer Retrieval and Generation
Large Language ModelEnterprise Document Intelligence [Vol.1 #6quater] – Question parsing takes one messy string and writes four…
16 min read -
Maximize your Claude Fable 5 usage
9 min read -
Why your regression coefficients keep changing, and what geometry has to do with it.
24 min read -
Cross-provider PR review with Codex in GitHub Actions, and why a second opinion from a…
25 min read -
A practical guide to building an evaluation workflow that catches retrieval failures, hallucinations, and performance…
10 min read
Editor’s Picks
-
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 -
A framework for aligning agentic AI with enterprise intent to ensure consistent scenario‑wide autonomous behavior.
19 min read -
That Is Embarrassing: Why Frontier AI Still Makes Things Up, and What to Do About It
Artificial IntelligenceThe best AI models still hallucinate. These hallucinations are sometimes funny, and sometimes cause actual…
22 min read -
They aren’t designed, you can’t help perceiving one anyway, and that makes them an engineering…
17 min read -
Hint: it is not GPU speed!
7 min read -
Map AI value, design workflows, redefine talent, upgrade the executive team, and measure the business impact.
7 min read -
How to decide when an AI agent should act on its own by using cost…
7 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
-
How Much Does It Actually Cost to Run a Local LLM? (Euros per Million Tokens, Measured)
Large Language ModelsI measured the actual GPU electricity for eight local models on one RTX 3090 —…
11 min read -
Long sessions rot quietly, well before any token limit is reached. Here’s why, and how…
20 min read -
Two techniques, two different problems, and why the question is not really “which one wins”
11 min read -
Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work
Large Language ModelLLMs don’t fail because they forget—they fail because they remember too much. As conversations grow,…
22 min read -
A practical next step into partitions, shuffles, joins, caching, and execution plans.
16 min read -
What our over-dependence on external consulting teaches us about delegating our minds to machines
25 min read
