-
Securing agents: tool-use permissions and the confused-deputy problem
An AI agent can be correctly authenticated, use legitimate APIs, and still cause a serious security breach.
-
Speculative decoding and other tricks that make inference 2x faster
A modern large language model can process thousands of input tokens in parallel, yet generating its response still involves a surprisingly inefficient process: producing one token at a time.
-
Expert systems to neuro-symbolic: what survived from GOFAI and why it’s coming back
The rule-based systems of the 1970s could explain their decisions, follow explicit constraints, and construct chains of logical deductions. They could also fail spectacularly when reality didn’t fit t
-
Running models locally: Ollama, llama.cpp, and ONNX Runtime on your own hardware
Running an AI model locally means executing its computations on hardware you control instead of sending every request to a remote inference provider.
-
Data quality as code: contracts, expectations, and stopping bad data at the door
A data pipeline can run successfully, pass every scheduled job, update every dashboard, and still produce completely incorrect business decisions.
-
Streaming responses: tokens, server-sent events, and perceived latency
Imagine two AI assistants answering the same question. Both require eight seconds to generate a complete response.
-
Imbalanced classes: why 99% accuracy can mean your model is useless
Imagine building a fraud detection system that achieves 99% accuracy . Your dashboard looks excellent. Your stakeholders are impressed. The model passes testing and gets deployed.
-
Kolmogorov–Smirnov and friends: goodness-of-fit and two-sample distribution tests
A service can have the same average latency, the same standard deviation, and the same request volume as yesterday—and still deliver a dramatically different user experience.
-
Entropy and cross-entropy: why your loss function is an information measure
Every time a language model predicts the next token, it makes a bet about the future. If it assigns a high probability to the token that actually appears, the bet was good. If it assigns a tiny probab
-
Convolutions from scratch: what a CNN actually sees, layer by layer
A convolutional neural network does not look at an image the way a human does. It does not immediately recognize a bicycle, a building, or a handwritten digit.