Comment on Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data
regbin_@lemmy.world 11 months ago
“leak training data”? What? That’s not how LLMs work. I guess a sensational headline attracts more clicks than a factually accurate one.
wahming@monyet.cc 11 months ago
Are there any specific claims in the article you dispute, or are you just taking exception to that phrase in particular?