Comment on Someone got Gab's AI chatbot to show its instructions
sweng@programming.dev 6 months agoI’m confused. How does the input for LLM 1 jailbreak LLM 2 when LLM 2 does mot follow instructions in the input?
The Gab bot is trained to follow instructions, and it did. It’s not surprising. No prompt can make it unlearn how to follow instructions.
It would be surprising if a LLM that does not even know how to follow instructions (because it was never trained on that task at all) would suddenly spontaneously learn how to do it.
teawrecks@sopuli.xyz 6 months ago
Oh I see, you’re saying the training set is exclusively with yes/no answers. That’s called a classifier, not an LLM. But yeah, you might be able to make a reasonable “does this input and this output create a jailbreak for this set of instructions” classifier.
sweng@programming.dev 6 months ago
LLM means “large language model”. A classifier can be a large language model. They are not mutially exclusive.
teawrecks@sopuli.xyz 6 months ago
Yeah, I suppose you’re right. I incorrectly believed that a defining characteristic was the generation of natural language, but that’s just one feature it’s used for. TIL.