Writing AI GPU inference kernels, optimizing for performance, and catching the ones that lie. AI is here to stay, gains more power by the day, alignment in safety and accuracy is paramount.https://danielrushton.com/https://danielrushton.com/writing/f1-the-whole-pipeline/https://danielrushton.com/writing/f1-the-whole-pipeline/Foundations: how an LLM is built, end to end, a toy LLM built from forty web pages.Sun, 25 Oct 2026 00:00:00 GMTFoundations