From Zero to Agents: Deconstructing the AI Revolution

Episode 01.01 ended by asking what it would take for a word’s vector to be computed fresh, for a specific sentence, using the words actually nearby right now — rather…

Continue reading →

Jul 27, 2026

junaidte14

Subword Embeddings and fastText: Solving the OOV Problem at the Vector Level (Ep.01.01)

Episode 01.00 ended by asking: does Module 00’s word-embedding machinery just apply directly to subword tokens like lowe + r + i + n + g, or does something break?…

Continue reading →

From Zero to Agents: Deconstructing the AI Revolution

Jul 27, 2026

junaidte14

Byte-Pair Encoding Explained: Why Tokenization Isn’t Just Splitting on Spaces (Ep.01.00)

Every episode of Module 00 quietly relied on .split() — text broken into whole words at whitespace, no questions asked. It was a deliberate simplification, flagged twice and never resolved.…

Continue reading →

From Zero to Agents: Deconstructing the AI Revolution

Jul 25, 2026

junaidte14

Why Are “Unrelated” Word Embeddings Never Actually at Zero Similarity? (Ep. 00.04)

Episode 00.03 ended with similarity(“king”, “apple”) = 0.74 — high, even though apple is the clearly unrelated word in that toy vocabulary — and asked why. There are two real…

Continue reading →

From Zero to Agents: Deconstructing the AI Revolution

Jul 25, 2026

junaidte14

Dense Word Embeddings Explained: From Co-occurrence Matrices to word2vec (Episode 00.03)

The last episode 00.02 left a real problem on the table: co-occurrence vectors give words meaningful, graded similarity — but they’re the same size as the vocabulary, mostly zeros, and…

Continue reading →

From Zero to Agents: Deconstructing the AI Revolution

Jul 25, 2026

junaidte14

How Does a Word Become a Number? The Representation Problem in AI (Episode 00.02)

Episode 00.01 landed on a working definition of intelligence built around selecting good actions under uncertainty, and generalizing efficiently. Every example we used to demonstrate that — the lookup table,…

Continue reading →

From Zero to Agents: Deconstructing the AI Revolution

Jul 23, 2026

junaidte14

What Is Intelligence, Really? (From Zero to Agents, Episode 00.01)

Last episode ended with a question. Here’s a definition worth pressure-testing (a very common first instinct — someone may say): “A system is intelligent if it can analyze requirements and…

Continue reading →

From Zero to Agents: Deconstructing the AI Revolution

Jul 23, 2026

junaidte14

From Zero to Agents: A Foundational AI/ML Course Built From First Principles (Episode 00.00)

Most “learn AI” content today teaches you to assemble — wire an LLM API into a framework, call it an agent, ship it. That’s a real and useful skill. It…

Continue reading →

Search

Categories

Recent Posts

Tags