pntha@lemmy.worldtoTechnology@lemmy.world•Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training DataEnglish
17·
10 months agohow do we know the ChatGPT models haven’t crawled the publicly accessible breach forums where private data is known to leak? I imagine the crawler models would have some ‘follow webpage-attachments and then crawl’ function. surely they have crawled all sorts of leaked data online but also genuine question bc i haven’t done any previous research.
i had never heard Robert pronounced “ro-bert” until just now in my head thanks to this obscure meme