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. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

Code accompanying the paper Pretraining Language Models with Human Preferences

Scan your AI/ML models for problems before you put them into production.

This repository includes the official implementation of our paper "Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics"

An implementation of iterated distillation and amplification

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

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

bbBOT is a felixble persona based branching binary sentiment chatbot.

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.

Code for our May 2024 AI security evaluation research sprint project

Interpretation of otherness and control