Encoding a person: what would it actually take?
If the goal is a working representation of how a specific person reasons in their domain, what's the actual stack? Walking through corpus, model, retrieval, eval, and where each piece breaks today.
Exploring the echoes reverberating through time left by the technology of yesterday as we embrace the technology of tomorrow.
Could there be a marketplace for AI training data?
The model providers scraped the open internet and called it fair game. The next phase needs an actual market for the data, and the structural pieces of that market don't exist yet.
Knowledge as a service: a thought experiment
If you could capture not just what someone knows but how they reason, and run that on local hardware, what would the artifact actually look like?
Style is not knowledge: and why the difference matters for AI
Capturing how someone writes is not the same thing as capturing what they know. Both are interesting capabilities. The conflation between them is going to cause problems.
GPT-4 first impressions: and a thought about who owns what they teach it
GPT-4 dropped a week ago. The capability jump is real. The ownership question it surfaces, about the corpus you use to teach it, is sharper than the marketing suggests.
The LLaMA leak and what \"your model on your machine\" could actually mean
Meta released LLaMA to researchers on February 24th. Three days later the weights were on 4chan. The rest of 2023 will be shaped by what happens next.
ChatGPT three months in: what changes when knowledge becomes a chat
Three months after launch, the most interesting thing about ChatGPT isn't the model, it's that millions of people changed how they ask questions overnight.
Echoes of the Machine: a framing for the next era
Four ways the engineering community is talking about AI right now. Two of them are wrong. Here's the framing this site is going to use, and what to expect from the threads that follow.
How To: Deploy Servers to Google Cloud Platform (GCP) with OneFuse and Terraform
Overview In this article we will go over how to deploy Servers to GCP with OneFuse and Terraform. We will only be using Naming and Static Property Sets (SPS) Groups in this article, but more Modules can be added to your TF files. Considerations We will assume you already have
How To: Deploy Servers to Amazon Web Services (AWS) with OneFuse and Terraform
Overview In this article, we will go over how to deploy Servers to AWS with OneFuse and Terraform. We will only be using Naming and Static Property Sets (SPS) Groups in this article, but more Modules can be added to your TF files. Considerations We will assume you already have
How To: Deploy Servers to Azure with OneFuse and Terraform
Overview In this article we will go over how to deploy Servers to Azure with OneFuse and Terraform. We will only be using Naming and Static Property Sets (SPS) Groups in this article, but more Modules can be added to your TF files. Considerations We will assume you already have
OneFuse Terraform Provider with vSphere
Editor's note (2026): The methodology described in this post is what I now call Decisions as Code. Property Toolkit was the OneFuse implementation of the same idea. See "Decisions as Code" for the current framing. In previous articles, I covered using the OneFuse Foundations Modules (Naming,