Category: Learning

Interactive Text Enhancer: A Tool for Embedding Clarifications | February 12 2026, 16:11

I whipped up this thing in just an hour. Do you think anyone besides me needs it?

Here’s the idea. Take any text – a Wikipedia article, for example. Highlight any segment, say something unclear. The LLM gives us an explanation, and instantly inserts a box right in the text which you can click to open the explanation. In this explanation, there might be something unclear too. We highlight it with the mouse from this explanation, and a box appears there too. This continues until everything is clear. All the boxes remain in the text, so you can always return to them. So, if the idea was unclear to me, maybe it will be to others, and then a ready link with explanations will come in very handy. The result can be shared with colleagues.

For explanations, not just the fragment is used, but also the context. For example, otherwise, the highlighted word Terrier would yield text about a dog breed, not about the search system.

My Ambitious 2026 Plan: From Galapagos Travel to Academic Achievements and Creative Pursuits | January 20 2026, 04:44

My plan for 2026:

– Travel to the Galápagos Islands, Ecuador for a week (summer)

– Finish and release a book on Information Retrieval (also summer, progressing slowly, first couple of chapters are already written. Already spent about 50-100 hours on this, the easy part)

– Release at least one scientific paper, probably on Data Mining (spring). Ideally, submit it somewhere to a journal (challenging). Already spent about 30 hours on this topic, a lot left to do.

– Make a step towards a PhD. Find professors, visit universities, understand the cost and assess my capabilities and resources.

– Continue studying fundamental mathematics and not die (linear algebra, calculus, probability theory, statistics, classical ML). In 2025, I spent about 200-400 hours on this topic.

– Continue studying Deep Learning and reach the “can teach” level. In 2025, I spent about 100-200 hours on this topic.

– Continue studying Data Mining/NLP.

– Update my book on RecSys, releasing version 2.0 with updates and corrections (autumn 2026)

– Make noticeable progress in painting and playing the piano. Specifically, learn Schubert’s serenade (Ständchen, D 889) completely and create at least one canvas that I wouldn’t be ashamed to give as a gift.

How Gemini Transformed Low-Resolution Previews into High-Quality PDFs | January 03 2026, 14:18

How unexpectedly useful Gemini turned out to be in a simple task – to create a high-quality PDF from a low-resolution preview. Nano Banana Pro was used, meaning, the output was raster, not vector. Look at the difference. Very often it is impossible to even make out the text, so from time out it turned into time dute;-). But overall, not bad.

Exploring the Magic of Neural Networks in Letter Prediction and Visualization | December 14 2025, 23:35

I am currently experimenting with training simple neural networks – primarily to automate the existing toolkit, and some things just seem like magic.

There is a database of 32,000 names. There is a neural network filled with random numbers. I start training, with only this list of names as input. The first layer of the neural network is embeddings, and I set the number of dimensions to 2 for easy visualization. And after 200,000 iterations of training, the system clearly separates vowels from consonants, and for some reason, places the letter “q” slightly apart from other consonants. It seems that this is because the letter ‘q’ almost exclusively predicts the letter ‘u’ (Queen, Quincy, Quentin).

It also very reliably separates vowels and consonants in Russian names. In Russian names, the letters b and l are somewhat away from the other consonants, as are the soft and hard signs (well, that’s understandable).

I wonder how it works. If trained on a normal corpus of texts, the difference would be very clear. Why are vowels separated from consonants? Apparently, from the network’s mathematical perspective, ‘a’ and ‘o’ serve the same function: they “trigger” the prediction of the consonant following them, so the alternation of vowels and consonants is to blame. But damn, it’s interesting 🙂

And since the model can predict the next letters, you might try running it on Russian. On a model with 30-dimensional embeddings, it invents names like: Byaketta, Afsena, Erakey, Zasbat, Daraya, Gaiomahad, Rain, Razhul, Gzhatsiy, Reben, Vureb, Durodira, Turuzhul, Regravgava, Razsan, Gabila, Avganzh, Raksi, Khalebkokhorta, Rather. The model – for those who understand – is this: input of 6×33 characters (because we take up to 6 characters of context), encoded into embeddings of 60, goes to a layer of 100 neurons, and from there back to 33 characters. Some nonsense, but at least it’s clear how it all works at all levels.

Modern Reading: More Words, Digital Shifts, and Surprising Data Insights from 2008 | December 14 2025, 22:33

An interesting study caught my eye, dating back to 2009. According to it, the modern human indeed reads significantly more than in the past, although the format of this reading has changed. The study suggests that in 2008, an average American consumed about 100,000 words a day (approximately a quarter of “War and Peace”) – this is an approximate number of words that passed through consciousness per day (via ears or eyes), calculated based on activity chronometry. This is 140% more than in 1980.

Therefore, contrary to the myth about the degradation of reading, at least in 2008, we processed 2.4 times more textual information than our parents’ generation. Moreover, the study only considered information consumed outside of work (at home, in transit, during leisure).

The structure of reading – if in 1960, 26% of words came from paper, by 2008 this share had fallen to 9%. However, digital media (internet, email, social networks) not only compensated for this decline but also tripled the total reading time. The reason — the internet, as it is predominantly a textual environment (web surfing, email).

But it’s interesting that although the Internet accounts for 25% of consumed words, it only makes up for 2% of bytes (since video on the internet in 2008 was of low quality). Thus, they estimated the information flow from different channels and converted it into bytes 🙂 Radio accounted for 19% of the time but only generated 0.3% of bytes (as audio requires less data). Voice communication (telephone) — accounted for only 5% of words and a negligible share of bytes, but it was the only fully interactive channel before the internet era. TV remained the main source of information by time in 2008 (41% of all hours) and quantity of words (45%), however, in terms of data volume (bytes), television was only second (35%), behind computer games.

Now about games, quite interesting. The main finding from the report: Games generated (or did in 2008) 55% of all “bytes” consumed by households. Meanwhile, they only accounted for 8% of user time. This is quite a controversial topic in their report.

Those 100,500 words — that’s an assessment of actual words that a person either read or heard. This is not a metaphorical “equivalent,” but an attempt to calculate the verbal information precisely. They took the consumption time of each media and multiplied it by the average word inflow rate for that channel. Reading (books, newspapers, internet texts): 240 words per minute. Email and web surfing – 240 words per minute. Television (dialogues in shows/movies): 153 words per minute. Radio: 80 words per minute (less because of many pauses and music). Music: 41 words per minute (song lyrics).

Link in the comments

Stages of Understanding Scientific Papers | December 10 2025, 19:38

As I periodically read scientific papers on my topic, I will try to articulate the levels of understanding the truth.

Level 0: “Read Later Folder” Downloaded the PDF, the title sounds genius, the abstract seems like the solution to all my problems. The file is forever buried in the ~/Downloads/Papers/ToRead folder.

Level 1: “Sumerian Cuneiform” Don’t understand anything at all. Random symbols, the Greek alphabet is over. “Orthogonal extrapolation of cognitive entropy within a quasi-stationary discourse inevitably induces a bifurcation of transcendental synergism.” Such materials really lower self-esteem. Most often from this level, you either fall back to zero, or gradually move to the second level.

Level 2: “Illusion of Competence” The Abstract is clear, the Introduction reads like a good detective story. But as soon as the main section starts, the text turns into a pumpkin. I can’t paraphrase it in my own words, only in general phrases: “Well, they trained a neural net… kind of.”

Level 3: “Formulas where needed and where not” The Abstract is clear, the first half of the article is also okay (architecture, pictures). But then comes formula (4), where “magic” happens. I take the authors’ word for it that equation (3) leads to (4) because, of course, I won’t check it. Beyond that — sheer horror and belief in a miracle.

Level 4: “Goldfish Effect” While reading — everything is crystal clear. The logic is solid, conclusions are obvious, the authors are smart. I close the tab, someone asks me, “What was the article about?” — and I freeze. My mind goes blank. If you take away the paper, I can’t reproduce even the idea because there essentially isn’t an idea, there is a process.

Level 5: “Armchair Expert” Everything’s clear, I can retell the essence over a beer. I know that Input transforms into Output, but the “black box” inside is still black. Give me a computer, I wouldn’t be able to reproduce even the skeleton because, it turns out, the article lacks half of the important stuff.

Level 6: “Critic-Practitioner” Everything is clear, I can recount, understand how to reproduce (even without their code). I see where they cut corners. I definitely know that the “state-of-the-art” result is achieved only thanks to a lucky seed or dataset and this strange trick in preprocessing, mentioned in the footnote on page 12.

Level 7: “Deconstructor” Hooray, I’ve understood everything and implemented it myself. It works worse than in the article, but I know why. However, I understand this work better than the second author (who just made charts). I see that all this complex mathematics over 5 pages boils down to two paragraphs in the middle.

Level 8: “Nirvana” The article is trivial. The idea is secondary, it was all in the ’90s with Schmidhuber, just named differently. Formulas are overcomplicated for importance. I can write the same in 10 lines of code and it will work faster. Reject.

If anything — I’m stuck somewhere between 2 and 4.

The Maddening Ambiguity of Mathematical Notation | December 02 2025, 15:30

If someone tells you that mathematics is an exact science, don’t believe them. Since I’m currently into data science as a hobby, I’m studying all sorts of things from different books and my brain is exploding at how this can happen in a science where every little detail should fit into a system, otherwise it goes by the wayside. Until it gets to notations. It’s a complete mess there. A set of dialects.

Take, for example, common logarithms. The “standard” for how to denote a logarithm depends on which room of the university you are in. In calculus and number theory, log(x) almost always means the natural logarithm ln(x) with base e. The derivative of e^x equals e^x. It’s “natural”. They’re too lazy to write ln. Yet, where decimal logarithms might appear (like in computer science), log(x) suddenly becomes decimal, and ln(x) is based on e.

The expected value E has an argument in square brackets. Meanwhile, the same square brackets in computer science are used for the step function 0/1.

Or if you see a vector – is it a column or a row? In classical mathematics, a vector is always a column. To multiply it by weights, we write T after the vector and then w for the weights. But in many papers, vectors are thought of as rows. And if you see y = xW+b, then x is not a column, because otherwise the dimensions wouldn’t match up. x here is a row. But in the next paper they write Wx+b. And there x is a column 🙂

Angle brackets . For the dot product, the symbol “⋅” is used, but it is hard to see, especially on a whiteboard, and I very often see that mathematicians use angle brackets for dot product. In general, angle brackets are used for the generalized concept of inner product, where the scalar product is a special case. signifies a certain abstract way to multiply a and b and get a number. Meanwhile, in quantum mechanics this would be written as . And for the scalar product, some use a circle with a dot or x in a circle.

And just for the sake of it, in Russia tangent is tg, while in the USA it’s tan. There’s also tan^-1 and arctan, which are the same, though x^-1 generally means 1/x

In-Flight French: Building a Language App on the Fly | December 01 2025, 15:45

By the way, yesterday morning, while waiting at the gate for my flight to Miami, I quickly wrote a French language learning app using Gemini based on an idea I sketched out to a friend while driving to the airport, and then used this app during the flight.

The idea is that in an unfamiliar foreign language text, the user first marks unknown words and then sees their translations — but without the original text, and then returns to the text itself — but no longer seeing the translations. It’s as if the “dictionary was in the next room.” The hypothesis is that this method helps better memorize than when the translation is shown immediately upon clicking on a word, and when no effort is needed.

I am pleased that creating the app from scratch to the finished version took only about 35-40 minutes, and then I used it for some time during the flight, without the internet. Since all translations of all words/phrases were already made in advance.

I just deployed it on Render. It’s also nice that demonstrating the code in action was free and took another 10 minutes.

https://readandlearn.onrender.com/

Rediscovering the 1986 “Chemical Trainer”: A Pioneer in Interactive Learning | November 23 2025, 15:55

At my home in Kolomna, I have a book called “Chemical Trainer” from 1986. I have never seen anything like it before or since.

The material of each of the 54 programs is divided into many small, very short sections, or categories. At the end of each category, one or more questions are posed. This is done to check whether the content of the category is truly understood. For each answer, there is a place in the book to jump to in order to see if the answer is correct. If the answer is wrong, it describes why and asks a new question. If correct — you move further in this quest.

These Germans in 1986 created an interactive textbook even before it became fashionable.

Unveiling “Recommender Algorithms”: A Comprehensive Guide on Recommendation Systems | October 25 2025, 17:36

I finally released a book on #RecSys! It’s called Recommender Algorithms, where I’ve compiled over 50 recommendation algorithms with detailed mathematical derivations, thorough explanations, and code examples.

https://www.testmysearch.com/books/recommender-algorithms.html

It all started early this spring in Germany, when I attended an ACM conference and sketched out the first structure of the book while analyzing the talks from the RecSys track. And now, just six months later, it has come to life.

Why did I write it? Because neither online nor in print is there a single, accessible resource that deeply explores recommendation algorithms of various types and purposes. There are articles focused on small subsets, but collecting and systematizing approaches—from foundational methods to the very latest—seems to have never been done before. I don’t know if I succeeded, but I’d love to hear your feedback.

Please like & share!

P.S. Click at READ SAMPLE to see the first 40 pages. The table of contents is there as well.

https://www.testmysearch.com/books/recommender-algorithms.html

https://www.testmysearch.com/books/recommender-algorithms.html