Lab

Articles

Technical writing on deterministic verification, Private AI, post-LLM architectures, applied epistemology, and local inference infrastructure.

June 2026 · AI Engineering · HPC · Deterministic Verification

Two technical papers, from both ends of the stack.

I'm publishing two documents that together show the same principle applied to different layers of the system: the hardware that holds twelve continuous hours of local inference, and the software that ...

April 2026 · Meta-knowhow · AI Engineering · Critical Thinking

Meta-knowhow: the new superpower in the age of AI

A professional's value was once measured by what they knew. Today, when AI systems aggregate and refine information faster than any individual, raw knowledge is no longer the differentiator. Controlli...

March 2026 · Architecture · LLM · Knowledge Graphs

GPUs are for interpretation. CPUs are for operational knowledge.

Most people think AI infrastructure ends with the model. It doesn't.

February 2026 · LLM · Neurosymbolic AI · Prolog

Fluency is not reasoning. LLMs need a logic layer.

More than a year ago, I wrote that a serious direction for AI was Transformers + Prolog. Today I would phrase it more precisely: LLMs need a declarative logic execution layer.

February 2026 · Epistemology · Semantic AI · Grounding

Semantics alone is not enough.

A system may connect concepts, organize symbols, and produce highly coherent language. It may relate sleep, stress, glucose, hydration, and behavior in ways that appear meaningful. But semantic cohere...

January 2026 · Medical AI · Clinical AI · Epistemology

From Prediction to Admissibility in Medical AI.

The point is not whether a model performs brilliantly on benchmarks, papers, or clinical datasets. The real question is different: what is the epistemic status of its output on the individual patient?

March 2026 · Self-hosted AI · Homelab · GPU

How I Test Vibration and Cooling Before Trusting Expensive AI Hardware.

Almost nobody talks about what happens when you actually turn it on.

December 2025 · Self-hosted AI · GPU · HPC

My first local inference test lasted 180 seconds.

Four NVIDIA K80 GPUs, GPT-J, standard tower server. At 85°C thermal throttling started. At 90°C, all four cards shut down. Adding aftermarket fans gained about 5°C. Irrelevant.

March 2026 · AI Engineering · Software Engineering · LLM

Epistemic Software Engineering.

The marginal cost of producing software with AI is approaching zero. The cost of knowing whether that software is reliable is not.

January 2026 · AI Engineering · DevOps · CI/CD

The smartphone as a control plane for software and compute infrastructure.

For decades, serious software systems required a workstation. That assumption is now breaking.

December 2025 · Cybersecurity · Self-hosted AI · Offensive Security

An abliterated model in public is a risk. Inside a controlled lab, it can be a capability.

People talk about self-hosting as if it were only about privacy or cost. The real advantage is controlling how the model behaves.

December 2025 · Self-hosted AI · Local Inference · AI Architecture

Everyone says self-hosting AI is about saving money. It's not.

It started with two things. Privacy as architectural boundary. And something I didn't expect.

November 2025 · Data Privacy · Local Inference · Data Governance

There's a sound most AI engineers never hear.

The hum of a local machine computing embeddings — no cloud, no API call, no data leaving the building.

September 2025 · Philosophy of AI · Godel · Human-AI

The incompleteness of artificial intelligence: humanity and AI, a necessary union.

Gödel's incompleteness theorem teaches us that in every logical-mathematical system there will always be truths that cannot be proven within the system itself.

June 2025 · Hybrid AI · Transformers · Prolog

Transformers and Prolog: the hybrid revolution of AI.

What happens when a poet and a mathematician join forces?

May 2025 · RAG · Embeddings · Semantic AI

The power of semantics: the IT of the future between RAG, embeddings, and the web as database.

From manual labor to the power of orchestrators.

November 2024 · Terraform · Ollama · Local LLM

Automatic cloud infrastructure generation with Llama3 and Ollama.

A practical case: Linux console + Python + Ollama (local LLM) + Llama3 model to generate ready-to-deploy Terraform scripts.

November 2025 · AI Economy · Markets · Philosophy of AI

The biggest bubble in history begins with a word.

Bank of England, IMF, ECB have broken a taboo: openly using the word "bubble" about Artificial Intelligence.

October 2025 · AI Use · Critical Thinking · Methodology

AI is not the problem. Using it without method is.

A man asked ChatGPT how to reduce salt and was told "use sodium bromide". Headlines: "AI is dangerous".

April 2026 · Local Inference · HPC · Systems Engineering

From thermal testbed to production: Qwen 2.5-Coder 32B on €300 of used GPUs.

What becomes possible when the engineering is done right. Four hardware generations later, the local inference node hosts a 32-billion-parameter model on two used GPUs.

March 2026 · System Thinking · Career · Methodology

From tool specialist to System Thinker: the thread of twenty years.

Twenty years in IT are not a collection of tools on a resume. They are a trajectory — and that trajectory has a precise direction.