Blogging in the Age of LLMs (fodder for token generators?)

This is not my usual type of blog post. It’s more of a reflection on where this blog and all blogs like mine belong. Especially in the age of instant “content creation” using LLMs. To give you the context, for years I kept writing blog posts here. Initially just simple notes for myself about the solutions for issues I faced while I was trying to build something. These were the kind of issues I couldn’t find any resources about (back then). But then I realised it’s starting to be useful for other people as well, since the issues I faced were pretty common ones. I was probably captured by blogging and SEO rules for some time as well in the early days, but I’d like to think I ditched those rules pretty quickly and kept on writing in my own style and language (simple language). This blog eventually led me to land a couple of book deals, and I became a published author sometime around 2017, 2018. Things were good, but over time life presented some challenges (as it usually does) and my blogging turned into more of an occasional habit.

Which brings me to this post. After I found some time to keep writing consistently again, I realised it’s 2025 and no one really reads blogs anymore (at least most that I know, don’t). Even the ones that do, would love a summary by LLMs. I realised LLMs have almost already replaced us bloggers and anything we write is simply part of some LLM response, mixed and mashed together with whatever else is “in there”. In a somewhat dark turn of events, we have simply turned into fodder for training mindless token generators. But such is the way technology moves. Forward! As long as the clock ticks away in the direction it always has, technology will also keep moving forward. Also, a full disclosure: I am considered an LLM expert these days (I didn’t ask for it). And this is not a post to bash LLMs. LLMs are here to stay and they are quite useful. For many things. Lots of things. Which brings me to the final point below.

I’m starting to see that this whole “AI revolution” will make these posts and blogs like this even more precious. Every letter, word and sentence you read on whatever screen you read it now is typed on a keyboard, by a human (allegedly human 🙃) And that is what I love about what LLMs have exposed to us, in us. Why do we do it? Why do we write? We do we do seemingly many other mundane tasks that can be easily automated by LLMs (some sooner than later, but eventually almost any task). I know have my answer as a blogger, which means I WILL keep writing. But you’ll need to think about your own answer. Why do you do it?

IMPORTANT NOTE: Although I am always grateful for what LLMs help me achieve in other daily tasks, they were NOT used to generate, edit or review this post in any way shape or form.

Using OpenCV ANN MLP to Train a Model on Iris Flower Dataset

Even though OpenCV is mainly a Computer Vision Library, it still contains a large set of very powerful mathematical functions, optimization algorithms and even GUI utilities that can be useful in other applications as well. Besides the fact that it’s open source and has a very permissive license, the emphasis on speed and performance which has always been the main goal of OpenCV, makes it even more appealing for commercial grade applications. That was my main motivation behind writing this post, and I want to walk you through it with a classical machine learning example, that is training a multilayer perceptron to classify Iris Flower Dataset entries.

Continue reading “Using OpenCV ANN MLP to Train a Model on Iris Flower Dataset”

Perspective Cropper 1.2.1 for Windows

I just released Perspective Cropper application for Windows platforms. I created this app a few months ago to quickly crop and correct the perspective distortion in a huge set of scanned documents and images. The pictures were taken using my smartphone from papers and documents laid on a table and from a few old family albums. Almost all of them had a lit bit of unwanted borders and perspective distortions and my goal was to just keep the parts I needed and remove the unwanted parts in addition to the correct and upright view of the images, as if they were scanned using a scanner.

Continue reading “Perspective Cropper 1.2.1 for Windows”

Computer Vision with OpenCV 3 and Qt5, Now Available for Preorder

It is one thing to become an author, but it is totally another level of joy, to be published by my most favorite publisher in the computer science industry. So, it is with great pleasure that today I can announce that my upcoming book about OpenCV and Qt is available for preordering on Amazon, and also from PacktPub. It’s titled “Computer Vision with OpenCV 3 and Qt5”, and it aims to teach both computer vision and application development for developers who are familiar with C++ (on an intermediate level), but want to learn about powerful cross-platform frameworks such as Qt and OpenCV with hands-on examples and clear instructions. The book is in its final stages of completion, so I’m also excited to announce that our goal is to make it available by the beginning of 2018 and we are working hard to make it happen. Here are the links to preorder:

https://www.packtpub.com/application-development/computer-vision-opencv-3-and-qt5