A New Trick Uses AI to Jailbreak AI Models—Including GPT-4
Adversarial algorithms can systematically probe large language models like OpenAI’s GPT-4 for weaknesses that can make them misbehave. Read the story here.
Adversarial algorithms can systematically probe large language models like OpenAI’s GPT-4 for weaknesses that can make them misbehave. Read the story here.