A post from Wired: Google, Apple, and Discord Let Harmful AI ‘Undress’ Websites Use Their Sign-On Systems
Single sign-on systems from several Big Tech companies are being incorporated into deepfake generators, WIRED…
When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure languages. Excited by this result, we attempted to reproduce it and found something unexpected.