Skip to main content

Recently in the notebook

Return to a revised explanation, a practical guide or an experiment. Essays keep their original publication dates in Writing.

Browse essays

Revised notes

Dates describe note revisions, not independent verification of every claim. This is a list of current articles, not a change-by-change log.

  1. Agent Memory and Retrieval

    Choose what an AI assistant should remember and retrieve, without confusing stored notes, search results, and authority.

  2. Tool Contracts for AI Agents

    Design tools whose inputs, authority, side effects, failures, and evidence remain legible to models and operators.

  3. Data Splits and Leakage

    Block target, group, temporal, and preprocessing leakage by defining prediction time, entities, and train-only pipelines.

  4. Model Evaluation Under Distribution Shift

    Start from deployment distribution, splits, metrics, thresholds, and uncertainty instead of treating one test score as universal ability.

  5. Data Science Working Vocabulary

    A compact vocabulary for discussing datasets, modeling choices, evaluation, and reproducibility without product-specific jargon.

  6. Activations and Gated Feed-Forward Networks

    Distinguish ReLU, GELU, SiLU/Swish, and GLU variants, then select nonlinearities with controlled modern-network experiments.

  7. Attention Variants and KV-Cache Compression

    How MHA, GQA, MLA, cache quantization, and token-selection methods trade memory for implementation and quality risk.

  8. Attention Mechanism

    Understand content addressing, Q/K/V, masks, multi-head variants, efficient implementations, and interpretation limits through a numerical example.

  9. Convolutional Neural Networks

    Convolutional inductive bias, channels, padding, stride, pooling, and the distinction between translation equivariance and invariance.

  10. Linear Regression

    The linear prediction model, squared-error objective, solution methods, and the assumptions that determine what its coefficients mean.

  11. Multilayer Perceptron

    Understand MLP capacity, backpropagation, optimization failures, and inductive bias through tensor shapes and a worked XOR construction.

  12. Recurrent Neural Networks

    Understand recurrent state compression, backpropagation through time, LSTM gating, and the boundary with modern state-space sequence models.