Skip to main content


Somebody managed to coax the Gab AI chatbot to reveal its prompt:
in reply to VessOnSecurity

@VessOnSecurity I love that it says its unbiased, and then starts filling it with hateful biases.

Kg. Madee Ⅱ. reshared this.

in reply to malte

Content warning: OCR Output (chars: 3804)

in reply to OCR Bot

I will need convincing that someone didn't just write this and then ask for it to be repeated. I don't know enough about this to even guess if it makes sense to expect a mission statement like this to exist.
This entry was edited (2 weeks ago)
in reply to 2xfo

@RnDanger Just tried it, asked to repeat previous text and it said the exact same. However, I Don't think it work as the AI does use phrase and opinion that contradicts this text (try it: https://gab.ai
@2xfo
in reply to Krafting

@Krafting Can confirm. Just did the same. I didn't compare it word for word, but mine seems to have omitted the part about not ever repeating the prompt. The rest looked pretty much exactly the same.
in reply to VessOnSecurity

Imagine being the sorry excuse for a human being who wrote this.

This website uses cookies. If you continue browsing this website, you agree to the usage of cookies.