Cross-Layer Transcoders: The Interpretability Tool That Might Be Lying to You
The interpretability tool designed to show you how a language model reasons can, under certain training conditions, produce circuits that match behavior while hiding the actual computation. This is not a minor caveat. It is a structural failure mode of the architecture.
Aurum: The Local AI Stack You Can Build in an Afternoon
Home inventory management is the most mundane problem AI has ever solved. It is also a perfect specification document for building a fully local, privacy-first, multi-modal AI application from scratch.
Voice cloning from 3 seconds of audio, running locally, at 97ms first-packet latency, open-source under Apache 2.0. The cloud TTS business model just got a serious challenge.
Ollama: The Easiest Way to Run Powerful AI Models Locally
Ollama is not an inference engine. It is a model manager with an inference engine hidden inside it. The community conflates these, and the confusion costs them performance.
