It stands to reason that if you have access to an LLM’s training data, you can influence what’s coming out the other end of the inscrutable AI’s network. The obvious guess is that…
So you’re saying that the ChatGPT’s and Stable Diffusions of the world, which operate on maximizing profit by scraping vast oceans of data that would be impossibly expensive to manually label even if they were willing to pay to do the barest minimum of checks, are the most vulnerable to this kind of attack while the actually useful specialized LLMs like those used by doctors to check MRI scans for tumors are the least?
So you’re saying that the ChatGPT’s and Stable Diffusions of the world, which operate on maximizing profit by scraping vast oceans of data that would be impossibly expensive to manually label even if they were willing to pay to do the barest minimum of checks, are the most vulnerable to this kind of attack while the actually useful specialized LLMs like those used by doctors to check MRI scans for tumors are the least?
Please stop, I can only get so erect!