hendrycks

Dan Hendrycks's starred repositories

JAILBREAK PROMPTS FOR ALL MAJOR AI MODELS

AGPL-3.02222 83 6

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Language:Jupyter NotebookMIT247 5 47

RuLES: a benchmark for evaluating rule-following in language models

Language:PythonApache-2.0209 2 3

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)

Language:PythonMIT99 3 2

AI that uses genetic algorithms to beat the game 2048

Language:Python400