WFGY 2.0 — Semantic Reasoning Engine for LLMs (MIT). Fixes RAG/OCR drift, collapse & “ghost matches” via symbolic overlays + logic patches. Autoboot; OneLine & Flagship. ⭐ Star if you explore semantic RAG or hallucination mitigation.

AI Safety research platform for studying personality drift in AI systems using mechanistic interpretability and clinical assessment tools. Complete simulation framework with neural circuit analysis, statistical drift detection, and intervention protocols.

📦 Redwood Research's transformer interpretability tools, conveniently packaged in a Docker container for simple and reproducible deployments.

Clinical AI Education: Learn to build, debug, and deploy medical AI through a real wound segmentation case study

I Asked It to Forget, but It Didn't — A Case of Miscommunication Between AI and Humans

Recursive Critique for AI-Generated Imagery - A framework for applying structural pressure, interpretability reasoning, and constraint-based analysis to expose image collapse and machine vision failure modes - and rebuilding images outside of engine defaults – No AI training, dataset scraping, or derivative generation permitted.