Dan Saattrup Smart

How I extended the Pi agent framework with custom extensions for local models, git [worktrees](https://git-scm.com/docs/git-worktree), and Neovim integration.

A follow-up to my previous post on setting up a local AI coding assistant in Neovim in 2026.

Setting up a local AI coding assistant in Neovim in 2026.

After getting lost of confused countless of times during my own home buying process, I decided to write this blog post to help others navigate the process.

Whenever OpenAI (or any other AI company to be fair) releases a new GPT model, we all tend to assume that the new model is always better than the predecessor - even if that model is also cheaper than the previous models.

In this post, we create a voice bot from existing tools out there.

How do you add a simple stand-alone dark mode component in Vue.js?

As ChatGPT has gained enormous popularity, open source versions of such generative language models finetuned on chatbot datasets have started to emerge.

This post covers the making of a personal website with Vue.js, including all the lessons I've personally learnt along the way from creating this very website.

I present my paper "Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap", joint with Carlos Mougan.

This post introduces the makefile and gives several examples of how to use makefiles for Python projects.

When using the int dtype in Python then its behaviour changes depending on the operating system, resulting in mysterious negative integers.

This is an introduction to graph convolutional neural networks, also called GCNs.

I introduce doubt, a Python library which helps machine learning models produce prediction intervals, giving uncertainty bounds to their point-estimate predictions.

DeepWalk was the first algorithm for producing node representations in arbitrary graphs.

We describe the PageRank algorithm, which was initially used to rank search results in the Google search engine.

Quantile regression forests (QRFs) is a way to make a random forest output quantiles and thereby quantify its own uncertainty.

This is an introduction to quantile regression models, which are models that natively outputs prediction intervals directly.

We present a novel method to produce prediction intervals for nearly any machine learning model, using bootstrapping.

We introduce the concept of parametric prediction intervals using normal theory, and how they are different to confidence intervals.

We introduce confidence intervals for sample statistics, both using normal theory with t-distributions and also using modern bootstrap methods, and includes a dummy example of Danish coffee consumption.

This post presents my project Scholarly, which can predict the arXiv category of a scientific paper using only the title and abstract.

This post covers a personal project of mine, developing a model that can split English words into syllables with a neural network, which is useful for both hyphenation as well as computing syllable counts.

Mean squared error and cross entropy are the most commonly used loss functions in machine learning.

This posts presents my Python package NaturalSelection, being a package that implements a genetic optimization algorithm, which can be used to evolve neural network architectures.

A pictorial description of what the singular value decomposition is actually doing, in terms of rotations, flips and scalings, with parallels to the eigenvalue decomposition.

A description of the normal, or Gaussian, distribution, and the key theorems surrounding it, the law of large numbers and the central limit theorem.

A description of the geometric and exponential distributions, and proving that they are the unique memoryless distributions.

A description of the uniform distribution, and why this distribution can be shown to be the universal distribution.

This first post presents the Poisson distribution, which counts the number of successes in a particular time interval, and has an associated result called the Law of Small Numbers.

Previously I covered the core model induction up to showing that all sets of reals in L(R) are determined.

I've previously mentioned an interesting characterisation of Woodin cardinals, that they are more or less characterised by the fact that we can do genericity iterations with them, i.e., that we can "capture reals" when Woodin cardinals are present.

Abstraction is so common in mathematics that we usually don't bat an eye when jumping between different levels of abstraction.

Absoluteness of wellfoundedness and Shoenfield absoluteness are two absoluteness results in set theory that are both used incredibly often.

Some of the first properties we learn about forcing notions are the notions of being atomless and being separative.

One of the first forcing facts that we learn is that kappa-closed forcings preserve all sequences of length kappa.

The previous two posts was dedicated to stating, explaining and applying a certain result in core model theory, the PD dichotomy, without using any inner model theory at all.

This is a continuation of my last post, in which I argue that core model theory can provide tools which other set theorists can use without having indepth knowledge of their proofs.

Inner model theory and core model theory might seem like their own niche in set theory, where you have to invest hundreds of hours just to get a glimpse of what's going on.

There are many different properties that forcings can have, whose consequences are usually well-known.

When doing set theory we tend to take pride in the fact that it's something unique, something that is doing things in a very different way from the rest of mathematics.

When doing set theory (or mathematics in general) we're working inside some universe, usually denoted by V.

The notion of distributivity comes from the Latin word distribut-, meaning "divided up", and has since evolved into how mathematics deals with things that are divided up.

When dealing with games in general, we can vary different parameters.

Looking at a map of the large cardinal hierarchy for the first time can be a dizzying experience.

There's a very neat way of encoding any set as a set of ordinals, which has the somewhat peculiar feature of it being hard (which here meaning that it requires the axiom of choice) to encode sets, but easy to decode them.

Mentioning the core model induction to a fellow set theorist is akin to mentioning that you're a mathematician to the layman --- you receive a reaction which is struck by a delightful mix of terror and awe.

The incompleteness theorems appear mysterious to many people, from sheer confusion of the statements themselves, to wrongfully applying the theorems to scenarios way out proportion, such as (dis)proving the existence of god.

It's quite standard nowadays to characterise the measurable cardinals as the cardinals kappa such that there exists a normal kappa-complete non-principal measure on kappa.

Last time we delved into the world of ideals and their associated properties, precipitousness and saturation.