Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git
14 points by lumbroso
A new system called ORRCF addresses oversight in AI-assisted programming by requiring models to provide detailed recommendations alongside their uncertainties and potential falsifiers for review. This structured approach aims to enhance the reliability and accountability of AI outputs, ensuring more informed decision-making in human-AI collaboration. Additionally, it introduces a version-controlled format for deliberation records, facilitating better tracking and management of AI interactions.