This is like the AI version of Manchurian Candidate. By silently seeding corners of the web with “wake words,” a nefarious party could trick GPT to train over them, thereby giving them a back door into the model.
It could also give a way of forcing an online entity into revealing that it’s a chat bot. Kind of gives me hope for the future…
It could also give a way of forcing an online entity into revealing that it’s a chat bot. Kind of gives me hope for the future…