Engineering notes on shipping LLM-powered products: on-device inference, deterministic state against language models, agentic build discipline.https://solshark.com/https://solshark.com/notes/whisper-on-the-neural-engine/https://solshark.com/notes/whisper-on-the-neural-engine/I built a dictation tool for myself in a day. The interesting part was not the app — it was discovering that the on-device model beat the larger one on speed and accuracy, and that the naming told me the opposite.Fri, 31 Jul 2026 00:00:00 GMTon-device AIspeech recognitionmacOSarchitecture