Terezija Semenski

@heynavtoor Breaking: Learning mathematics and software engineering is more important than ever. Math is the bridge from software development to software engineering. It keeps your mind sharp, and you need it more than ever in the AI era.

🚨BREAKING: Andrej Karpathy just killed coding forever. He calls it "VIBE CODING" Describe what you want in English, and AI builds the entire app. No syntax. No debugging. No $150K CS degree. Here are 9 Claude prompts that turn anyone into a software engineer:

When people ask me define ML Engineer

1 equation. Powers Netflix recommendations. Compresses images. Finds topics in documents. Linear algebra isn't abstract. It's infrastructure. Free roadmap → bio

Where SVD appears in ML: • Recommendation systems (Netflix, Amazon, YouTube) • Latent semantic analysis • Image compression and denoising • PCA (PCA is just SVD applied to centered data) • Word embeddings • Data preprocessing

Netflix has 15,000 movies and 200 million users. That's 3 trillion possible user-movie combinations to search through. Instead of brute-forcing it, they use one equation from linear algebra: SVD. Here's how it works 🧵👇

Did you eat some π today? I did. Then I ate some more. Then more. It just... kept going. Infinitely. Send help. And more pie. Today is March 14th 2026, so Happy Pi Day!

@Math_files A horror story to look for every mathematician

@haider1 Can you please share links to studies?

gpt-5.4 pro leap, as a generalist, agentic research model, is massive it is already being used to work autonomously on private beta math-proof solving and auto-formalization across many domains, with similar progress in theoretical physics. and much more is coming

@ninja_maths I would love to hear an interview with your students as it seems way too fast pace even for very talented students.

For anyone wondering how a third-grader can complete six years' worth of math in a single year. This knowledge graph spans 3,000 math topics, from 4th grade to the university level, providing the perfect basis for mastery learning. Students can go as fast or far as they want! There are no restrictions whatsoever. The only requirement is that they must demonstrate mastery of each topic before moving on to the next. Kids are capable of incredible things when given that kind of freedom and support.

52! (52 factorial, you get it by multiplying 52*51*50*49*…*2*1) is a number so absurdly large that if you shuffled a deck every second since the Big Bang, you still wouldn't have repeated a single arrangement. Math is wilder than fiction.

There are more possible chess games than atoms in our galaxy. But here's what's crazier: there are more ways to shuffle a deck of 52 cards than all of those chess games combined.

@SmitBPatel2 Thanks, I appreciate your feedback

@TSemenski Great job. Thanks @TSemenski

Most ML engineers use matrix multiplication every single day. Only a few of them can explain what it's actually doing. Here's how matrix multiplication REALLY works, explained visually so it finally clicks 🧵👇

📌 If you want a FREE ML engineering roadmap : 1. Follow me. 2. Like the post. 3. Subscribe to: mathmindset.substack.com

That's matrix multiplication in ML. Given these inputs and these weights, what are the outputs? Once you see it this way, you'll never forget it.