“Universal and Transferable Adversarial Attacks”: Researchers Jailbreak GPT

“Universal and Transferable Adversarial Attacks”: Researchers Jailbreak GPT Researchers with Carnegie Mellon’s Center for AI Safety have published a paper describing a method for developing adversarial attacks (a.k.a. jailbreaks) that … Read more

Anthropic’s Latest Model

Anthropic’s latest model can take ‘The Great Gatsby’ as input Anthropic has improved its text-generating AI model, Claude, by essentially adding more “memory” to it. TechCrunchKyle Wiggers