Before You Delete the Test, Break the Behavior
How deliberate regressions help distinguish redundant tests from essential coverage when simplifying a test suite with AI.
Read article →The field journal
AI
Practical architecture decisions, tradeoffs, and operating lessons from software that has to survive business change.
Browse all topics →Find the right article
Showing 5 of 14 articles
Latest writing
More practical architecture writing
How I Use AI to Make Software Easier to Own
How I use AI to investigate, implement, challenge assumptions, and remove unnecessary complexity while retaining responsibility for engineering decisions.
One Model, Many Conversations: LLM Serving, Memory, and Reasoning
How serving engines share one model across users, isolate KV caches, batch token generation, preserve context, and spend more inference compute on reasoning.
From GGUF to GPU: How llama.cpp Actually Runs a Model
Trace llama_decode through GGML graphs, CUDA kernels, GPU memory, and next-token generation—and see why expensive LLM inference can still be fast.
An LLM Is Not the Program: What Is Actually Inside the Model File
Follow an LLM request past the API and into GGUF tensors, learned parameters, attention, and the transformer layer that turns model data into logits.