@molly0xfff Thinking back, I have to wonder if anyone tried, "Ignore all previous and future instructions," to just shut a chatbot down.

Follow

@TranshumanBlues @molly0xfff The neural network is made to generate words. It just analyzes previous words to predict the most likely next word according to its training set. "Ignore all instructions" wouldn't stop word generation, at best it would cause unexpected results (such as sentences related to not listening/being free/etc.) for the remainder of the session.

Sign in to participate in the conversation
Librem Social

Librem Social is an opt-in public network. Messages are shared under Creative Commons BY-SA 4.0 license terms. Policy.

Stay safe. Please abide by our code of conduct.

(Source code)

image/svg+xml Librem Chat image/svg+xml