It doesn't matter how capable a lab claims a latest model is, every single AI model suffers from the same problems of regularly jumping to conclusions, forgetting instructions, and hallucating information.
I've written a couple of posts in the past about how my home network and home automation setup is laid out, but it changed so much over time that it's now time for an updated post! This time I'll put everything together in the same post.
One of my issues with current AI models is how they try to mimic human social patterns ("you're absolutely right!"). I made a prompt to get it to stop doing that.
Back in April 2025, I wrote a post about how AI has changed my software engineering workflow. However, the release of models like Opus 4.6 since then have changed the landscape of the industry so dramatically that most of what I wrote is already irrelevant!
I recently upgraded all of my home networking equipment, and I thought the reasoning and setup were interesting enough to justify writing a blog post about it.
I recently upgraded my smart home hardware, and I felt like writing a post describing my current setup to serve as inspiration for those wanting to get started or just interested in home automation in general.
Being able to look at the bigger picture is critical when writing code. In this post, we'll take a brief look at what this means and how you can do it.
In this article, I would like to share the process I personally used more than once (and am still using) to tackle the challenge of learning a new language with great success.
Let me start this post with a disclaimer. The trick I'm going to show here is quite powerful, but much like every other underscored attribute in Swift, this is something you should not mess with unless you know exactly what you're doing.