fintex
@_yusufknl • 2,254 subscribers
AI researcher by day nihilist by nature · crypto · models · chaos
Videos
As someone who's been shipping LLMs since the GPT-2 days, this lecture on cross-entropy from a Stanford math grad is the closest thing to an ML PhD qualifying exam I've ever seen released publicly for free. Everyone thinks language models predict the next word. They don't. They compress language. Once you see the math, you can't unsee it. 33 minutes. Bookmark & watch today.
fintex352,576 Aufrufe • vor 26 Tagen
As someone who's spent 3 years fine-tuning ML models, this lecture on neural networks from a Stanford math grad is the closest thing to a no-bullshit "day one of ML" briefing I've ever seen released publicly for free. Everyone thinks neural nets are magic. They aren't. They're 13,000 dials - a matrix multiplication, a sigmoid squish, done. Once you see the math, "AI" stops feeling mysterious. 18 minutes. Bookmark & watch today.
fintex330,207 Aufrufe • vor 25 Tagen
In 1948, Claude Shannon invented the math behind every LLM you use today. He tested it by making his wife guess the next letter in a book. A Stanford-trained mathematician just released a 32-minute walkthrough of this exact history - and why the "next-token prediction" story of GPT-5 is actually wrong. Bookmark & watch this weekend. The alternative is a graduate info-theory course + 3 semesters of your life.
fintex285,466 Aufrufe • vor 24 Tagen
As someone who's built with modern LLM architectures, this Laplace transform lecture is the closest thing to a "why Mamba works" explainer I've ever seen released for free. Everyone thinks transformers are the only path to modern LLMs. State space models like Mamba and S4 challenge that using math Laplace built in the 1780s. This video shows why. 25 minutes. Bookmark & watch today.
fintex109,738 Aufrufe • vor 15 Tagen
As someone who reads every transformer paper that drops, this Fourier series lecture is the closest thing to a Google FNet explainer I've ever seen released for free. Everyone thinks attention is what makes transformers powerful. Google replaced attention with a 200-year-old Fourier transform. It nearly matched BERT and ran 7x faster. 25 minutes. Bookmark & watch today. Then read the article below - I broke down the 5 pieces of math the AI hype skips.
fintex100,409 Aufrufe • vor 21 Tagen
Schrodinger's equation, Neural ODEs, and every LLM built on Mamba use one operation: raising a matrix to a power. Sounds like nonsense until you see it. A Stanford math grad just released a 27-minute walkthrough starting from a mass on a spring and building up to quantum mechanics. Publicly free. Bookmark & watch this weekend. Same operation, from 1926 to 2025.
fintex43,310 Aufrufe • vor 13 Tagen
As someone who trains LLMs, this 20-minute gradient descent video is the closest thing to a "why the memorization vs generalization debate matters" explainer I've ever seen released for free. Everyone thinks neural nets learn features. They often just memorize. The video walks through the 2017 paper that shocked the field: shuffle your labels randomly and modern networks will still fit them perfectly. 25 minutes. Bookmark & watch today.
fintex15,922 Aufrufe • vor 12 Tagen
Keine weiteren Inhalte verfügbar