← Back to context

Comment by globular-toast

14 hours ago

I wrote about this a year ago: https://blog.gpkb.org/posts/just-send-me-the-prompt/

Sending LLM outputs to people is worse than useless, because you don't even know what they prompted with. For all you know it was "write me a paragraph justifying my opinion".

Or you could learn to verify what they sent you. Geezus fuck. How about knowing why did they ask this, and not some other question.