Writing

Learnings, reflections, paper summaries, and notes.

  1. Outside the Agentic LoopAIEveryone in the valley reduces an AI agent to a while loop. The loop is the easy five percent. This is a plain map of the other ninety five, the part that actually makes an agent good.
  2. All (Machine) Learning is just a measure of surpriseLearningHamming's back-of-envelope math made me realize my own math fundamentals weren't strong enough, so I rebuilt it from the floor (exponentials, logs, surprise) until I got to cross-entropy loss, finally explaining itself from the bottom up.
  3. A Month Off CodeReflectionsReflections from a month in San Francisco where I took a deliberate break from coding agents, two hackathons, and what stepping back taught me about what I want to build.
  4. Build something usefulBuildingModernizing a Dental Practice
  5. Cli Is Cool AgainReflectionsHow we are moving away from GUIs with the rise of Coding Agents
  6. [Learnings] 001 - AI Applied (Prompt Engineering and Evaluation)LearningsThe two main ways AI Engineers boost their outputs — Prompt Engineering and Evaluation.
  7. [Reflections] 001 - The Thinking GameReflectionsWatching The Thinking Game about DeepMind and processing where humans fit in the age of AI.
  8. [Learnings] 000 - AI Applied (Foundations)LearningsA practical guide to working with AI models — API basics, tokens, embeddings, and system prompts.
  9. [Reflections] 000 - ResetReflectionsGetting back to writing. Building. Doing.
  10. [Note to Self]ReflectionsA quick note about getting back to writing and learning.
  11. [PapersSummarized] Deep Residual Learning for Image Recognition (2015)PapersK. He et al. — How residual connections solved the degradation problem in deep networks. Rating: 3/5.
  12. [PapersSummarized] Very Deep Convolutional Networks For Large-Scale Image Recognition (2015)PapersK. Simonyan et al. — VGG paper showing deeper is better with smaller filters. Rating: 1/5.
  13. [PapersSummarized] ImageNet Classification with Deep Convolutional Neural Networks (2012)PapersA. Krizhevsky et al. — The paper that lit the deep learning revolution. A must read. Rating: 5/5.
  14. [PapersSummarized] Backpropagation Applied to Handwritten Zip Code Recognition (1989)PapersY. LeCun et al. — The first successful large-scale commercial application of backpropagation. Rating: 3/5.
  15. [NotesToSelf] Intuition Behind Why ReLU Works So WellReflectionsBreaking down why ReLU is the go-to activation function in neural networks.
  16. [PapersSummarized] Learning Representations by Back-Propagating Errors (1986)PapersG. Hinton et al. — The seminal paper that laid the foundation for all deep learning. Rating: 2/5.
  17. [PapersSummarized] A Few Useful Things to Know about Machine Learning (2012)PapersP. Domingos — 12 practical insights every ML practitioner should know.
  18. [PapersApplied] Mining Association Rules between Sets of Items in Large Databases (1993)PapersR. Agrawal et al. — The Apriori Algorithm for finding item relationships in transaction data.
  19. [PapersApplied] Induction of Decision Trees (1986)PapersJ. R. Quinlan — The precursor to C4.5 and C5 algorithms for creating decision trees.