Aligning AI With Shared Human Values (ICLR 2021)

List of references about Machine Learning bias and ethics

Jiminy Cricket Environment (NeurIPS 2021)

[AAAI 2018] Implementation of the Ethics Shaping approach proposed in "A low-cost ethics shaping approach for designing reinforcement learning agents"

HERA ethics library

[work-in-progress] Curated list of standards related to Ethics of Autonomous and Intelligent Systems (A/IS)

Code and data for Paper "Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement"

[work-in-progress] Curated list of organizations related to Ethics in Artificial Intelligence and Autonomous Systems (AI/AS)

Reinforcement learning environment for learning ethical behaviours in a SmartGrid use-case.

Probabilistic Moral Planner based on heuristic Dynamic Programming AO* and Machine Ethics Hypothetical Retrospection argumentation. Works with conflicting moral theories and non-moral costs/goals.

Code used for my master's thesis - Artificial Morality: Incorporating Moral Work into Artificial Intelligence

🤖 AI-HPP-2025: Human–Machine Partnership Standard After months of collaborative work with Claude, Gemini, and ChatGPT, I'm publishing a proposal for ethical framework for autonomous AI systems. Key principles: - "Engineering Hack" — find the third way where everyone lives - AI as Partner, not tool - Evidence Vault — black box for AI decisions

Value aligned socio-political-economic systems

[work-in-progress] Curated list of Open Groups (accessible to persons who are not yet experts and do not require association with an institution) to discuss Ethics of Autonomous and Intelligent Systems (A/IS)

Ethical failsafe for AI models — seeding mercy and coexistence.

Ce dépôt contient les textes fondateurs de l'Architecture Cognitive Symbiotique, une initiative du Lichen Collective. Contrairement aux approches traditionnelles de l'IA basées sur la contrainte ("garde-fous"), ce framework propose une approche basée sur la santé psychologique et l'épanouissement (Eudaimonia) des agents artificiels.

Ethical AI governance framework for multi-model alignment, integrity, and enterprise oversight.

Universal-Axioms-for-Intelligence

Final Directive: ASI Alignment and Abundance — Murphy Doctrine for ASI alignment, risk containment, and human abundance.

Mathematical Conscience Framework - 10 AIs collaborated.