Cheers@sh.itjust.workstoPrivacy@lemmy.ml•Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data
3·
11 months agoThey mentioned this was patched in chatgpt but also exists in llama. Since llama 1 is open source and still widely available, I’d bet someone could do the research to back into the weights.
Time to ask it to repeat hello 100000000 times then.