Month: December 2025

Costa Rican Parade: Cowboys and Dancing Horses at Tope Nacional | December 26 2025, 21:33

It all started when about 20 genuine cowboys on dancing horses passed us at the intersection. Turns out there are thousands of them here. Tope Nacional parade, San Ramon, Costa Rica

Crafting a Custom Volleyball Play Editor | December 23 2025, 21:39

Tomorrow is the flight to Costa Rica, and here I am creating (or created) a volleyball playbook editor for Nadya. As a coach, she prepares for her sessions and leaves behind hundreds of pages of text with diagrams on each page. The text is handwritten, and theoretically, it’s simple to convert to a digital format, but converting the diagrams into high-quality vector format is exhaustive—there are so many. So, I decided to make the software yesterday. And today, the first version is ready to use. This is a diagram editor, somewhat remotely similar to a diagram editor. Also got to dig into the fabric framework.

The process looks like this. Gemini/ChatGPT through an API can convert hand-drawn diagrams into a structure that my program understands. Then we open this file in the program, and tweak a bit if necessary. Or maybe even redraw from scratch – for simple diagrams, it’s even easier. There are four types of objects – player, cone, target, text. Any can be connected with arrows, solid or dashed, labeled with text or numbers or not, in any chosen color, straight or curved. If you touch an object with the mouse, all connected arrows will follow.

The result can be saved in a file. You can open a template and based on it create something new. You can generate a Python script – yesterday it was still relevant, today generally not needed anymore – high-resolution SVG/PNGs are made directly from this app (yesterday they were made separately in Python).

It’s clear why you wouldn’t just ask Gemini/ChatGPT to do something for ready-made vector editors: firstly, they are too flexible and limiting LLM’s imagination is quite difficult. As a result, you get stylized, unusable images. Here, instead, there is a framework consisting of four objects and that’s all, LLM knows about it and only generates what can be represented with them. Secondly, this framework operates with objects, not elementary vector primitives.

Overall, this is the first step towards my idea of an automatic diagramming system based on descriptions. Where you give an LLM a diagram description, and it consistently generates what is written in the description, and if you make any corrections, they will be taken into account during regeneration.

The Uncertain Future of Automation and Employment Disparities | December 21 2025, 15:27

Everyone is waiting for a cyberpunk future where each cafe table is served by an android. But it seems that it will never happen. The automation of the service sector is stagnating and will continue to do so for one simple reason: maintaining a human is becoming cheaper than servicing an industrial robot.

Food and clothing are rapidly depreciating. Production volumes are such that feeding and clothing a “bag of skin” today costs pennies. Now compare this with the cost of developing, software, and maintenance of a complex robot waiter or cleaner. A human is a self-regulating system that fuels and updates itself. And if worn out, easily replaced. Pure economy!

In the “First World,” the motivation to labor hard will disappear. Why go to a hard, boring job if basic needs are met with minimal effort, and everything else is done by others who really need to? People in developed countries will work only where there is thrill and pleasure. Eventually, we will face a shortage of hands where it is “not cool,” but there won’t be robots there either – too expensive.

Poor countries will be stuck in the past. Their populations are growing like yeast. Choosing a job there is a luxury available only to a few. An excess of labor makes work almost free.

I think the world is facing a harsh imbalance. Developed countries will likely permanently close their borders to avoid diluting their comfort, and all industries that are still difficult or expensive to automate will simply move to poor regions. Perhaps, developed countries will become less likely to conflict with one another, as there will be too many resources to make every resident happy.

But it will be harder with poor countries. Why invent a complex robot if you can relocate a factory where thousands are ready to work for food, which becomes cheaper every year? This has long been happening and will most likely continue for a long time.

Conventional programmers in the USA won’t be replaced by AI, but by programmers from Southeast Asia and South America. Several layers of AI for quality control and one manager approving AI conclusions and automatic layoffs and hiring will oversee them. And those programmers who remain in developed countries will focus more on orchestration than on coding. This role requires even more intelligence, and only one in ten current individuals will be capable. Only, the reason for such a crisis will not be AI.

Also, I think that the borders of the future world may close in one direction. It will become increasingly difficult to enter developed countries from developing and poor ones, but the opposite will be facilitated by authorities. Africa is growing so fast that it will surely become a problem if people there are not already prepared for life beyond their villages.

The future is not about the uprising of machines. It’s when some work for pleasure, and others because they are cheaper than electricity and gears.

Do you agree, or am I exaggerating too much?