You build a project. It’s clean, well-structured, cohesive. You know every corner of it. Then life happens: the project moves to a different team for day-to-day maintenance. They bring their own style, their own habits. Things start to drift. Not dramatically, just… gradually. The codebase gets a little messier with every handover.

Now drop an AI agent into that codebase. Same story, amplified. It doesn’t know the history, the constraints, the “we do it this way because of that incident three years ago”. Every change it makes risks introducing side effects it can’t even reason about.

You’ve probably experienced this already: you ask AI to do something, it produces code that looks plausible but breaks your style, misses your constraints, creates subtle bugs. You fix it, try again, hit the same wall. And you start to wonder if this AI thing is all hype.

It’s not. But your codebase isn’t ready for it yet.

You’ve got a middleware. It reads a comma-separated list of allowed hosts from configuration. Or maybe it loads a dictionary of route mappings, or parses a set of feature flags into a lookup table. The config value can change at runtime and you need to pre-process it into something your middleware can actually use on every request.

How hard can it be? 🤷

Lately, I’ve successfully self-hosted a decent private chatbot and even run a near real-time voice-to-text model locally. So I thought: why not try running a local coding model? I have a pretty decent gaming rig, so it should be able to handle it, right?

Well, it turns out: not really. I spent the whole weekend trying to set up a local coding model and ran into a pile of issues. The models are huge and hungry. Even with my gaming rig, I was barely able to get it running, and it was extremely slow. I ended up dealing with more technical issues than coding tasks.

One of the most common questions I get asked is: “Which AI model should I be using with GitHub Copilot?”

Open GitHub Copilot today and you are greeted with a dropdown menu that looks like a wine list. Sonnet? Gemini? Opus? GPT-5? 🤯 It used to be simple, but now it can be paralysing.

Which one is best? It depends on what you are trying to achieve, how complex the task is, and how you want to manage your credit usage.

My rule of thumb is simple:

• Start cheap to think and iterate.
• Pay for certainty when the blast radius is big.

Now that the Windows 10 May 2020 Update is finally available to everyone, without requiring to join the Windows Insiders program and install preview versions, it’s finally time to embrace WSL2.

WSL2 is the second iteration of the Windows Subsystem for Linux which finally allows running linux virtualized inside Windows. This new version brings real virtualization using a real linux kernel, but, compared to a traditional virtual machine, it runs on a lightweight hypervisor getting close to bare-metal performance.

This will also be used by Docker under the hood, boosting the start-up time and general performance of our containers. Sweet! Furthermore, with WSL2, VPN connections automatically propagate to linux correctly, which is great news when working from home.

So, let’s stop talking and get to update our Ubuntu 18.04 WSL environment to Ubuntu 20.04 running on WSL2.

GitHub Actions are a great free tool to have continuous integration of your opensource .NET library for free, directly into GitHub, saving you from setting up other tools and linking accounts. Setting it up can feel a daunting task but, if you follow this guide you are going to be able to set it up in 10 minutes!