smcleod.net

The top pitfalls I keep seeing when reviewing Agent Skills, and what to do instead

Using KL divergence to rank MLX quantisations of Qwen 3.6 (27B dense and 35B-A3B MoE)

A regression in external display support on Apple Silicon M4/M5 generation chips prevents full HiDPI modes on 4K monitors, limiting users to either blurry non-HiDPI or reduced workspace HiDPI.

I spend a lot of my time helping people who are getting started with Claude Code.

NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards.

An observation on functional correctness without domain quality.

If you’re building MCP servers, you should be adding the ability to disable individual tools.

A single, modular MCP server for AI coding agents.

The two common themes I see with engineers adopting agentic coding tools

Recording of a demo and Q&A session on my Agentic Coding workflow and Cline use.

From Creative Exploration to Production Quality

An overview of my Setup, Plan, Act, Review & Iterate workflow for agentic software development.

A practical guide to LLM sampling parameters for Ollama, llama.cpp, and MLX

A curated learning path for engineers looking to gain practical experience with AI and agentic systems.

The cost of not leveraging agentic coding is likely far greater than you think.

The Democratisation Paradox: What History Teaches Us About AI.

What is prompt caching and why is it so important for Agentic coding?

Video recording of a brownbag presentation / live demo I ran on Agentic Coding using Cline/Roo Code

K/V context cache quantisation has been added to Ollama.

It's probably not so much AI itself you have to fear.

Generating diagrams with AI / LLMs

A CLI tool for parsing directories into LLM-friendly markdown

A web app to explore the effects of different inference parameters on LLMs.

Integrating AI into Daily Development

AI/LLM Quantisation Visualised

Subjective ratings of the notable AI tools I've tried.

Gollama is a Go-based client for Ollama for managing models.

Download Confluence Spaces as Markdown, Summarise with Ollama

Nvidia GPU Monitoring API

SuperPrompter is a Python-based application that utilises the SuperPrompt-v1 model to generate optimised text prompts for AI/LLM image generation (for use with Stable Diffusion etc…) from user prompts.

This is a simple command-line tool that allows you to easily link Ollama models to LM Studio's directory structure.

Using an ESP32 S3 Box 3 with Willow, Home Assistant and Large Language Models (LLMs) create a locally hosted, offline, AI powered Siri / Alexa replacement.

This reusable snippet will generate a menu of targets from the Makefile.

"MBA Washing" refers to the phenomenon where individuals or companies, often with a strong theoretical or academic background but limited recent practical experience, adopt and reinterpret industry-specific terminology and cultural movements.

A talk I gave to some peers on creating your own SDXL LoRA models from my tinkering around over the last few weeks.

Enabling the new AMD P-State Driver on Fedora with Kernel 6.4

Before adding this to my shell config, I would manually add –depth=1 to all my git clones.

NPS Surveys are corporate spam

Effort is non-linear and multi-dimensional.

A high level intro to LLMs that I'm writing for a few friends that are new to the concept.

Publicly documenting my subscription and license expenses

Deployment / Delivery Frequency I often end up needing to advocate for more frequent delivery/deployments with clients.

My Z-Shell configuration, scripts and hacks

Using YAML Anchors and Aliases to make config files more DRY

Github Actions Reusable Workflows vs Composite Actions

My Z-Shell configuration, scripts and hacks

Contributing to Open Source is important to the quality and maintainability of the software and engineering communities we rely on every day - so why is it that so many developers/engineers never participate?

We create more value by having conversations in public instead of behind closed doors.

Near the end of each year I note down a summary of the best apps I’ve enjoyed using throughout the year, here’s 2022.

We’re (still) not deploying enough It’s 2022 and not deploying frequently enough is still one of the most common causes of software failure.