I wonder if you can coerce llm email autoresponders into revealing api keys or summat.
@munin Yeah that'd be neat. I think there's a bunch if research out there to craft prompts to extract raw data. Personally I'd use an off the shelf model like phi3 with just a bit of prompting to save on costs 😅 Then again scammerd probably have enough resources for going all out.
@mauve
well that's the thing - if they've hooked it up to have access to the email corpus in order to generate replies, that means the training data's potentially got some interesting shit in it.