Writing
Articles
Technical opinions, analysis and commentary on the engineering choices behind the tools we use.
What Actually Happens When You Press Enter? How Generative AI Works
Your prompt is cut into tokens, each token becomes a vector of 1,024 numbers, 28 transformer layers rework those vectors, and out comes a probability for every possible next token. Pick one, add it on, repeat. I measured each step on a small open model: cat sits nearest kitten, 42 of 448 attention heads link "it" to "animal", and it confidently named the capital of a country that doesn't exist.
I Fixed My Testing Tool. Did It Find More Bugs?
After fixing the problems I found, WebMCP Resilience caught 15 of 19 timing bugs, up from 11, with no false alarms on correct code. Each fix earned its place, and one introduced a bug of its own that the rerun caught.
I Built a Tool to Find Timing Bugs. Does It Find Any?
An ordinary check caught none of 19 timing bugs. WebMCP Resilience caught 11, with no false alarms on correct code, and showed me exactly where it falls short.
Building GenAI on a Tight Northern Budget
How I keep experimenting with GenAI without spending a fortune.