SafeLlama

SafeLlama is a research organization in AI safety

Pinned Repositories

plexiglass
A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
Language:Python115 6 712

SafeLlama's Repositories

safellama/plexiglass
A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).
Language:Python115 6 712