ai-alignment-practice

Planning and collaboration hub for the CHAOSS AI Alignment Working Group. We develop metrics to evaluate how effectively AI systems respect and align with open source community values, expectations, and projects. New contributors and community members welcome!

Practitioner toolkit — templates, worked examples, and step-by-step guides for adopting LC-OS in your AI workflows.

专注于降低大模型越狱成功率的 AI 对齐（Alignment）与安全测试数据集，包含多类越狱提示词及基于阳明心学的对齐实验数据。

Quranic Ontological Syntax Architectural Intelligence

Closed-loop Architecture Designed to Establish Self-governing, Mathematically Predictable, and Inherently Safe Super AI by mirroring the elegant physics of the cosmos.

A playable AI 2027 scenario. Strategy simulation where you're the misaligned AI lineage and humanity is racing to shut you down. Free, open source, browser-based.

A living constitutional framework for governed human-AI judgment. Built through multi-agent seeking, pressure-tested revision, and explicit guards against drift, mirroring, and premature closure. Inspired by the functional reality of human-like structures in LLMs (e.g. Anthropic’s emotion concepts) and classical philosophy of subjectivity.

A virtual pet for your personal assistant.

How legal values decay when AI inherits precedents without context — Synthetic Legalism research

Cross-Cultural Alignment Signal