Researchers were able to jailbreak five state-of-the-art (SOTA) large language models (LLMs), including Open AI’s ChatGPT-3.5, GPT-4, Gemini, Claude, and Meta’s Llama2 using ASCII art.

Researchers have discovered a new way to hack AI assistants that uses a surprisingly old-school method: ASCII art. It turns out that chat-based large language models such as GPT-4 get so ...