Frontal AI models vulnerable to jailbreaking; four major frontier companies tested their safeguards.
Read the original at www.wired.com→I watched a new tool try to get around the model safeguards of four major frontier companies. You might be surprised by how they performed.
Original headline: "It’s Frighteningly Easy to Jailbreak Some Frontier AI Models"
Coverage timeline
- Jul 29, 18:30 UTC Wired AI lead source It’s Frighteningly Easy to Jailbreak Some Frontier AI Models