anomnom@sh.itjust.workstoTechnology@lemmy.ml•Google AI chatbot responds with a threatening message: "Human … Please die."English
4·
5 days agoI also wonder if this isn’t something that someone has “told” an LLM, and that now it’s just parroting it back. It all fits with my opinion of the AI craze.
I wonder if it’s related to training on website comments, which often role the same trajectory.