Comment on Researchers train AI chatbots to 'jailbreak' rival chatbots - and automate the process

Rivalarrival@lemmy.today ⁨10⁩ ⁨months⁩ ago

Therefore every AI chatbot maker needs to apply protections,

I’m pretty sure the instructions to create an AI chatbot have been published, and are available for a sufficiently capable AI to draw from. What keeps a primary, morality-encumbered AI from using those instructions to create a secondary, morality-unencumbered AI?

source
Sort:hotnewtop