It’s self delusion, nothing more. Broken logic
Comment on Somebody managed to coax the Gab AI chatbot to reveal its prompt
mhague@lemmy.world 2 months ago
I don’t get it, what makes the output trustworthy? If it seems real, it’s probably real? If it keeps hallucinating something, it must have some truth to it? Seems like the two main mindsets; you can tell by the way it is, and look it keeps saying this.
Natanael@slrpnk.net 2 months ago
Olgratin_Magmatoe@lemmy.world 2 months ago
Given that multiple other commenters in the infosec.exchange thread have reproduced similar results, and right wingers tend to have bad security, and LLMs are pretty much impossible to fully control for now, it seems most likely that it’s real.