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

Interpretation of otherness and control

Code for our May 2024 AI security evaluation research sprint project

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. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

Code accompanying the paper Pretraining Language Models with Human Preferences

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.

bbBOT is a felixble persona based branching binary sentiment chatbot.

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

An implementation of iterated distillation and amplification