Recent Posts

• 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.… Read more: Teaching AI Models: Gradient Descent
• Needle 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,… Read more: Needle in the Haystack: Embedding Training and Context Rot
• Measuring 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… Read more: Measuring Meaning: Cosine Similarity
• AI Paradigm Shift: From Rules to Patterns
  Post 1/N Every piece of software you’ve ever shipped or have seen shipped works the same way. A developer sits down, thinks through the logic,… Read more: AI Paradigm Shift: From Rules to Patterns
• Seq2Seq 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… Read more: Seq2Seq Models: Basics behind LLMs
• Word2Vec: 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… Read more: Word2Vec: Start of Dense Embeddings
• Advertising 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… Read more: Advertising in the Age of AI
• Breaking the “Unbreakable” Encryption – Part 2
  In Part 1, we covered the “Safe” (Symmetric) and the “Mailbox” (Asymmetric). The TL;DR: we use high-speed symmetric safes to store our data, but we… Read more: Breaking the “Unbreakable” Encryption – Part 2
• Breaking the “Unbreakable” Encryption – Part 1
  If you’ve spent any time in tech, you’ve heard of AES, RSA, and Diffie-Hellman. We treat them like digital duct tape—they just work, they keep… Read more: Breaking the “Unbreakable” Encryption – Part 1
• ML 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… Read more: ML Foundations – Linear Combinations to Logistic Regression
• Privacy 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… Read more: Privacy Enhancing Technologies – Introduction
• Privacy 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,… Read more: Privacy Enhancing Technologies (PETs) — Part 3
• Privacy 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.… Read more: Privacy Enhancing Technologies (PETs) — Part 2
• Privacy Enhancing Technologies (PETs) — Part 1
  How Your Data Gets Protected Every time you browse a website, click an ad, or make a purchase, data flows through dozens of systems. Companies… Read more: Privacy Enhancing Technologies (PETs) — Part 1
• An Intuitive Guide to CNNs and RNNs
  When your phone recognizes “Hey Siri,” a CNN is probably listening. When Google Translate converts your sentence into French, an RNN (or its descendants) is… Read more: An Intuitive Guide to CNNs and RNNs
• Making Sense Of Embeddings
  Post 2/N When you search on Amazon for “running shoes,” the system doesn’t just look for those exact words – it also shows you “jogging… Read more: Making Sense Of Embeddings
• How CNNs Actually Work
  In the ever-evolving world, the art of forging genuine connections remains timeless. Whether it’s with colleagues, clients, or partners, establishing a genuine rapport paves the way for collaborative success.
• How Smart Vector Search Works
  In the ever-evolving world, the art of forging genuine connections remains timeless. Whether it’s with colleagues, clients, or partners, establishing a genuine rapport paves the way for collaborative success.