- Published on
All Posts
- Published on
A working glossary of LLM inference workloads running on GPUs- Published on
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.- Published on
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.- Published on
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.- Published on
A practitioner's mapping of the DTA's mandatory agentic AI controls to real Bedrock Guardrails configuration, tested against a live guardrail.- Published on
A tool to search across Commonwealth legislation, for Innovation Month 2026- Published on
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.- Published on
Creating a neural network using base R- Published on
Extending Bayesian Networks to model time series- Published on
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.- Published on
How probabilistic network structures can be learnt from data- Published on
The Ceiling of my vibes: Building a Game with LLMs when you are not a game developer- Published on
Implementing spectral clustering from scratch in R- Published on
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.- Published on
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.- Published on
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.- Published on
Your new addiction to fast, flexible data pipelines. The quickest high from local to cloud.- Published on
"Building and hosting Vue web apps on Drupal" presentation resources- Published on