Teaching AI Models: Gradient Descent
Post 1b/N In the last post, we established the big idea: machine learning is about finding patterns from data instead of writing rules by hand. But we skipped a critical question — how does the machine actually find the patterns? When someone says…
Read MoreNeedle in the Haystack: Embedding Training and Context Rot
Post 2c/N You’ve probably experienced this: you paste a 50-page document into ChatGPT or Claude, ask a specific question about something buried on page 37, and the model either ignores it, gives a vague answer, or confidently cites something from…
Read MoreMeasuring Meaning: Cosine Similarity
Post 2b/N In the previous posts, we established that embeddings turn everything into points in space and that Word2Vec showed how to learn those points from context. But we glossed over something critical: how do you actually measure…
Read MoreSeq2Seq Models: Basics behind LLMs
When you use Google Translate to turn a complex English sentence into Spanish, or when you ask Gemini to summarize a long email, the computer isn’t just looking at individual words. It’s following a path. It’s remembering where the sentence started…
Read MoreWord2Vec: Start of Dense Embeddings
Post 2a/N When you type a search query into Google or ask Spotify to find “chill acoustic covers,” the system doesn’t just look for those exact letters. It understands that “chill” is related to “relaxing” and…
Read MoreAdvertising in the Age of AI
When you search for a product today, ads quietly shape what you notice. When you scroll Instagram, ads compete for slices of your attention. For decades, advertising has existed because humans have a simple limitation: we cannot evaluate everything. This…
Read MoreML Foundations – Linear Combinations to Logistic Regression
Post 1a/N Every machine learning model — from simple house price predictors to neural networks with billions of parameters — starts with the same fundamental building block: the linear combination. Take some inputs, multiply each by a weight, and add…
Read MorePrivacy Enhancing Technologies – Introduction
Every time you browse a website, click an ad, make a purchase, or train an ML model, data flows through systems. Companies need this data — for analytics, measurement, personalization, and product improvement. But they also have legal, ethical, and…
Read MorePrivacy Enhancing Technologies (PETs) — Part 3
Privacy-Preserving Computation and Measurement In Part 1, we covered how organizations protect data internally — minimization, anonymization, query controls, and differential privacy. In Part 2, we explored secure collaboration — clean rooms, identity…
Read MorePrivacy Enhancing Technologies (PETs) — Part 2
Secure Collaboration Without Sharing Raw Data In Part 1, we covered how individual organizations protect data internally — minimization, anonymization, query controls, and differential privacy. But modern business often requires multiple parties to…
Read More