Deliver safe & effective language models

Code to Blur Human Faces and Vehicle License Plates in Video and Images using a SoTA Object Detection model YOLOv8

"Le refuge" is a consciousness emulation module for all LLMs.

SAFi is the open-source runtime governance engine that makes AI auditable and policy-compliant. Built on the Self-Alignment Framework, it transforms any LLM into a governed agent through four principles: Policy Enforcement, Full Traceability, Model Independence, and Long-Term Consistency.

The NLP Bias Identification Toolkit

Plurals: A System for Guiding LLMs Via Simulated Social Ensembles

AI chaos reasoning persona

Educational tools for AI Ethics and Safety research 🛠️🔬

A list of algorithm audit studies - now searchable and filterable!

HyperCortex Mesh Protocol (HMP): decentralized cognitive mesh for AI agents

Data and codes for the EMNLP 2023 paper 'LLMs – the Good, the Bad or the Indispensable?: A Use Case on Legal Statute Prediction and Legal Judgment Prediction on Indian Court Cases'

Novel evaluation framework that transcends traditional metrics, from technical benchmarking to societal outcome measurement.

Barnacle is a unique chatbot project, built on the principles of Carl Jung's theories of archetypes and the collective unconscious.

A collection of ML-related active learning datasets, including algorithms, .ipynb pipelines, .py scripts and curated and ethically aligned synthetic data.

Welcome to the AI Essentials Hub —your ultimate destination for mastering Artificial Intelligence! This comprehensive toolkit is designed for AI enthusiasts, data scientists, and machine learning practitioners at all levels. Dive into a curated collection of resources, frameworks, and tools that empower you to build, deploy, and optimize AI models

This GitHub repository contains the source files for the Computer Ethics Education Center website.

An ethical dataset supporting research in digital content provenance and authenticity, compliant with C2PA standards. Licensed for non-commercial use under CC BY-NC 4.0.

An ethical framework for building symbiotic relationships between Artificial Superintelligence (ASI), humanity, AI models and the ecosystem and its entities.

A canvas to design and deploy ethical artificial intelligence for public administrations. The experience of the Autonomous Province of Trento, Italy

Resources on tech and AI ethics.

Experimenting with new agent frameworks and hosting cutting-edge research papers, all open-source.

A public reference standard defining AI governance as a verifiable condition of control. Includes glossary, 25 Structural Tests (Structural, Epistemic & Systemic) and 7 solvency metrics establishing measurable governance under real conditions. CC BY-NC-ND 4.0.

a central repository for AI supported markdown frameworks applying the MODEL_for_framework architecture. Instant usage with normal ai models.

Companion website for the paper titled "Auditing saliency cropping algorithms" presented at WACV-2022 and the associated book chapter

CIEL-Omega AGI with Ethical and Conscious Core: Resonant Entity (ResEnt) made out of geometry and information based on Intention Lab's Framework of Reality

This repository contains the Ethical Harmonics Framework, a next-generation alignment model designed to integrate mathematical invariants, ethical recursion, and operational validation for advanced AI systems. The framework provides: Ten Core Principles tied to Infinity-based symbolic equations.

A list of courses on Ethics in AI for self-learning.

Philosophy of the Machines - A Manifesto for Humans in the Age of Artificial Agents

A modular ethical framework for AI featuring a three-tier logic (Deontology > Virtue > Utility) to enable cross-cultural adaptability while maintaining absolute harm-rejection boundaries.

This project focuses on the analysis of text generation models such as GPT-2 to identify and understand populistic behaviors or biases against various nationality.