ai
33 posts
-
Video: best practices for AI-assisted coding with GitHub, tests and CI
A 52 minute video with five demos of coding with an AI agent under version control, tests and continuous integration, using OpenCode and free NRP models.
-
Set up an AI coding agent with free NRP models
Set up OpenCode with the free NRP models in a few minutes, with safe permissions, model advice and the seminar checklist.
-
Keeping interactive tutorials up to date with an orchestrator and AI subagents
How to keep browser-based tutorials working with an orchestrator, a browser executor and a documentation improver, instead of hoping nobody follows the outdated step.
-
Write slides in Markdown with Marp when working with AI agents
Why keeping presentations in Markdown and building them with Marp works well with AI agents, with a clean reusable theme and an example repository.
-
Managing projects with GitHub and AI agents: the structure problem
In my previous post about managing projects with GitHub and AI agents I described how I organize events and workshops with a single GitHub repository as the source of truth, issues for every activity, and an agent per collaborator.
-
Living with a local 27B LLM on a Mac mini: capable enough and (almost) fast enough
I run an Apple M4 Pro Mac mini in the office as a private LLM server: a 27B Qwen 3.8 model, served over my Tailscale tailnet, used every day by my coding agent to handle emails, Trello cards, and general project work.
-
Mac mini as a private LLM server: the technical setup
This is the technical companion to the experience post: how the Mac mini is set up, how every service runs, and where the configuration lives. The benchmark details (prefill, decode, context stress test, agent context sizes) are here too. The data-center comparison is in the comparison post.
-
Same 27B model, two worlds: Mac mini vs a data-center GPU
How much does datacenter hardware buy you over an Apple Silicon dev box? To get a feeling for it, I set the NRP managed LLM service, which hosts Qwen3.8-27B (api name qwen3-small) in bf16 on their Nautilus GPU fleet, against my Mac mini (the high-level story is in the experience post, the full setup in the setup post), which serves the same model quantized to NVFP4 on the MLX engine.
-
Managing projects with GitHub and AI agents
Organizing conferences and workshops can quickly become overwhelming when plans, decisions, contracts, and meeting notes are scattered across multiple platforms.
-
See if your opencode session is still working in ChromeOS Overview
Running opencode in a ChromeOS Crostini terminal, you have to keep switching back to the window to know if the agent is still working. Desktop notifications only tell you when something finishes.
-
Python for HPC at SDSC Summer Institute 2026
I updated the Python for HPC session I taught at the SDSC Summer Institute 2026 (August 7, 2026). The material was heavily rewritten for this year - a substantial rework, not a refresh of the 2025 version.
-
Running AlphaFold3 and OpenFold3 protein-ligand structure prediction on SDSC Expanse
I built two self-contained, reproducible projects that run realistic (non-toy) protein structure prediction on a single SDSC Expanse GPU node: one with DeepMind AlphaFold3 (via nf-core/proteinfold) and one with the fully open OpenFold3 (MCL1 protein-ligand ensemble).
-
Preview local documents from a Linux AI agent in ChromeOS Chrome
A small agent skill bridges Crostini and ChromeOS so coding agents can open generated PDFs, images, and HTML in the Chromebook's normal Chrome browser.
-
Configure opencode to use TritonAI Developer API at UC San Diego
A step-by-step tutorial for adding UC San Diego's TritonAI Developer API as a provider in opencode, including how to request access, find available models, and test them.
-
Control your existing ChromeOS browser with any AI coding agent
A reliable architecture for safely connecting multiple AI coding agents to an existing ChromeOS browser session using the Playwright extension.