A real Weave project that regression-tests three OpenAI models against the exact reply format your app depends on.

What large operators can teach us about turning alert fatigue into faster, safer service assurance

I built a system that automatically discovers, verifies, and applies relevant requirements from earlier interactions without asking the user where they came from.

Why AI coding makes software design more important

Frequentist confidence intervals and Bayesian credible intervals answer different questions, and confusing them can distort product decisions

Clarifying the math behind Anthropic’s representation workspace

Better understand the intent of your coding agents

Why autonomous agents expose a new explainability problem in fraud detection

Moving from static model assignment to intelligent, task-level LLM selection.

A practitioner's guide to estimating what an opt-in AI feature actually did, when nobody randomized it.

Why AI coding makes software design more important

Frequentist confidence intervals and Bayesian credible intervals answer different questions, and confusing them can distort product decisions

Why autonomous agents expose a new explainability problem in fraud detection

A model is only as reliable as the assumptions behind it

Understanding permutation symmetry in deep learning, and what it means for weight averaging and model merging

A real Weave project that regression-tests three OpenAI models against the exact reply format your app depends on.

I built a system that automatically discovers, verifies, and applies relevant requirements from earlier interactions without asking the user where they came from.

Statistical thinking beyond formulas

A context window can be technically complete and still describe a world that no longer exists. I built a deterministic benchmark to measure the cost of acting on stale context.

Using LDA for dimensionality reduction in classification problems

Improving reinforcement learning for complex physics