Dennis Schubert@denschub@mastodon.schub.social
@utzer@soc.utzer.de or maybe, just maybe - hear me out - a "please don't lie to me" prompt actually doesn't do anything to prevent AI from lying to you, because if it did, OpenAI would have already done it.
wild concept, I know.
utzer :verify: @utzer@soc.utzer.de
@denschub@mastodon.schub.social I can only tell what I know from my experience.
Usually I use prompts like in this example.
https://chatgpt.com/share/689b346a-2638-8008-977f-39451d6b1b41