Building the AR and MA parts of ARIMA model mathematically

ARIMA Modelling In-depth Dive 1 - Auto-Regressive (AR) and Moving Average (MA)

Web-scraping the prices of properties sold in Canberra (politely) from AllHomes and Domain

Web-scraping Canberran house prices

Connecting Nifi to Teradata

Chain rule

A deep dive into the ABS’s modified Serfling model for estimating excess mortality

Excess mortality - a look at the ABS’s robust regression method

Looking into relationships between Hip-hop artists by analysing the network graph of their collaborations

Hip-hop collaboration network graph

How blackjack rounds were simulated in JavaScript for justBlackjack

Simulating blackjack with JavaScript

How UX/UI was implemented in justBlackjack, a browser-based blackjack simulator

Setting the table for justBlackjack - a JavaScript blackjack simulator

Binary classification with random forests and XGBoost

The Spaceship Titanic

A public reader for Commonwealth Acts that shows defined terms where they are used, built from machine-readable AKN XML.

Lex AU Explorer: Reading Commonwealth Legislation With the Definitions Built In

A three-layer pipeline (rules-as-code, discrete choice model, agent-based model) for behavioural policy simulation that keeps what is measured separate from what is assumed, calibrated against a real adoption survey.

Simulating Policy Adoption with Rules-as-Code, DCM and ABM

Serving a 70B model on rented GPU since I can't run that on my MacBook Pro, then breaking it on purpose and measuring recovery.

Renting a GPU to run an LLM

A working glossary of LLM inference workloads running on GPUs

Running your own LLMs (for beginners)

au-radar is a RADAR-consistent benchmark of how well AI describes and reaches Australian federal services. It scores Australia 5.32, and finds that a robots-respecting agent is blocked at the free legal database but not at the silent government register.

Can an AI Agent Reach an Australian Government Service?

ClauseKit runs five bodies of law through an LLM extraction pipeline. 171 of 262 extracted rules never produce a yes or no, and that gap is the result.

How Executable Is Legislation as Code? An Experiment

Porting a fine-tuned sentence embedding model into a Drupal 10 module, running ONNX inference in-process via PHP FFI. No Ollama, no external API, no vector DB.

ONNX-Native Fine-Tuned Semantic Search in Drupal

A practitioner's mapping of the DTA's mandatory agentic AI controls to real Bedrock Guardrails configuration, tested against a live guardrail.

Mapping DTA's New AI Rules to AWS Bedrock Guardrails

A tool to search across Commonwealth legislation, for Innovation Month 2026

Act Alike: Are Terms Defined Consistently Across Legislation?

A decompose-then-verify pipeline that checks each claim in an AI output against its source document, and an honest look at what the RAGTruth numbers actually say about it.

Grounding Inspector: Does Your LLM Know When It's Lying?

Neural networks from scratch

Extending Bayesian Networks to model time series

Dynamic Bayesian Networks

How to use your existing Notion kanban board as the cockpit to manage your running AI agents, demonstrating human intervention and agent memory across runs.

Observing and Steering your AI Agents via Kanban

How probabilistic network structures can be learnt from data

Structure Learning in Bayesian Networks

The Ceiling of my vibes: Building a Game with LLMs when you are not a game developer

Vibe coding a game in 2026 as a data engineer

Implementing spectral clustering from scratch in R

Spectral Clustering from scratch

Fine-tuned MiniLM exported to ONNX and run inside an existing Spring Boot app. No vector DB, no Bedrock per query, no GPU. The post I needed when I started.

Auto Search: Semantic Search Inside the JVM

How I built a two-mode spatial decision support tool that lets health planners ask plain-English questions about GP coverage gaps and get optimised facility placement recommendations with briefing-quality narrative.

Building an AI-Powered Health Facility Planner for Australian PHNs

How I built a one-click Slack shortcut that turns incident threads and Q&A chains into structured Confluence KB articles using the Claude API.

Building a Documentation Agent with Slack, Claude, and Confluence

Your new addiction to fast, flexible data pipelines. The quickest high from local to cloud.

Quackpipe, running DuckDB local and on AWS Glue

"Building and hosting Vue web apps on Drupal" presentation resources

Building and hosting Vue web apps on Drupal

"Navigating the AI-Augmented Future of Software Development" presentation resources

Navigating the AI-Augmented Future of Software Development

Easy way to migrate AWS SageMaker Notebook using S3

Migrate AWS SageMaker Notebook to JupyterLab 4

Reading AWS SageMaker asynchronous inference `CustomAttributes` header in R using Plumber

Plumber R reading AWS SageMaker custom attributes

Clear trash on AWS SageMaker Notebook to free up disk space

Free up disk space on AWS SageMaker Notebook

"Building Web Applications with Vue.js" presentation resources

Building Web Applications with Vue.js

"Java with GraalVM and AWS Lambda" presentation resources

Java with GraalVM and AWS Lambda

Cloning Git with Large File System (LFS) on various AWS services

Using Git LFS on AWS

Creating a simple hash table in C using concepts from CS50x

Implementing a Hash Table in C

If programming languages were people, thoughts from a Generative AI

Enabling parallel and asynchronous processing in your Plumber APIs using the future package

Asynchronous Processing in Plumber APIs with Future

Syndromic surveillance for the early detection of epidemics

The Farrington Flexible algorithm for aberration detection

For Things I Do Often but Forget How To Do

Data Wrangling Cheat Sheet

An overview of how to resolve merge conflicts in Git

Advanced Git Workflows

Basic Git Workflows

An introduction to using Git, covering basic concepts

Getting Started with Git

Web-scraping basketball player stats using rvest to analyse fantasy league performance

Web-scraping to get an edge in the NBA fantasy league draft

An example of an Apache Beam pipeline written in Python that writes data to BigQuery

Python Beam and DataFlow to write data to BigQuery with a custom Docker image

Using `gargle` and Application Default Credentials to authenticate with GCP from R

Authenticating with Google Cloud Platform from R

How to use `bigrquery` and `googleCloudStorageR` to create external tables in Google BigQuery

All Posts