s7ryph@kbin.socialtoPrivacy@lemmy.ml•Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data
8·
11 months agoTeam of researchers from AI project use novel attack on other AI project. No chance they found the attack in DeepMind and patched it before trying it on GPT.
I find it very accurate for cooking related tasks. I find it to be 90-95% on even the wildest recipes. And developing flavour profiles is something it’s also very good at.
I know that’s not a huge thing for most people but recipe sites are so terrible and flooded with trash I appreciate the time saved. I bring this up because the article suggests it should only be used as a starting point.