Decision-Engine

Introduction Apple Silicon changed everything for ML inference. The unified memory architecture allows models to run at speeds that were previously impossible on consumer hardware. But most ML frameworks weren’t built for this reality. MLX is Apple’s answer—a framework designed from the ground up for Apple Silicon. And Laya-MLX applies this framework to the System 1 decision engine, achieving 13.4ms latency on M3 Max hardware. That’s not just fast. It’s fast enough to make real-time typed decisions feasible in applications that previously required cloud APIs. Customer service routing, fraud detection, content moderation—all running locally on your Mac. ...

Introduction There’s a fundamental tension in AI systems: the models that reason best are slow, and the models that are fast don’t reason well. Most developers accept this tradeoff. Laya rejects it. The project achieves what seemed impossible: typed decisions—multiple choice, scoring, yes/no—at 33 milliseconds per question, trained with reinforcement learning against strictly proper scoring rules, across 100+ languages. No text generation. No parsing. No hallucination surface. This isn’t a distilled LLM pretending to decide. It’s a different architecture entirely: a non-autoregressive encoder that evaluates questions in a single forward pass. The implications extend beyond speed. When your decision model outputs a label, not text, you eliminate an entire category of failure modes. ...