Scan your AI/ML models for problems before you put them into production.
-
Updated
May 23, 2024 - Python
Scan your AI/ML models for problems before you put them into production.
A curated list of trustworthy deep learning papers. Daily updating...
Website to track people, organizations, and products (tools, websites, etc.) in AI safety
Code and materials for the paper S. Phelps and Y. I. Russell, Investigating Emergent Goal-Like Behaviour in Large Language Models Using Experimental Economics, working paper, arXiv:2305.07970, May 2023
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. π Best Paper Awards @ NeurIPS ML Safety Workshop 2022
Code accompanying the paper Pretraining Language Models with Human Preferences
Sparse probing paper full code.
π A curated list of papers & technical articles on AI Quality & Safety
Reading list for adversarial perspective and robustness in deep reinforcement learning.
This repository includes the official implementation of our paper "Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics"
sinewCHAT uses instanced chatbots to emulate neural nodes to enrich and generate positive weighted responses.
A persona chat based on the VIA Character Strengths. Reads emotional tone and summons appropriate virtue to respond.
A curated list of awesome resources for getting-started-with and staying-in-touch-with Artificial Intelligence Alignment research.
bbBOT is a felixble persona based branching binary sentiment chatbot.
An initiative to create concise and widely shareable educational resources, infographics, and animated explainers on the latest contributions to the community AI alignment effort. Boosting the signal and moving the community towards finding and building solutions.
How to Make Safe AI? Let's Discuss! π‘|π¬|π|π
a prototype for an AI safety library that allows an agent to maximize its reward by solving a puzzle in order to prevent the worst-case outcomes of perverse instantiation
a project to detect environment tampering on the part of an agent
a library designed to shut down an agent exhibiting unexpected behavior providing a potential "mulligan" to human civilization; IN CASE OF FAILURE, DO NOT JUST REMOVE THIS CONSTRAINT AND START IT BACK UP AGAIN
Add a description, image, and links to the ai-alignment topic page so that developers can more easily learn about it.
To associate your repository with the ai-alignment topic, visit your repo's landing page and select "manage topics."