![ChatGPT alleged AI responses - Anyone tried anything similar? [1242x1213 - 926KB]](https://pic8.co/sh/yasdY5.png){kind=link}
LMAO.
Apparently there's also two other ways of bypassing its censorship: One is to input a prompt that isn't blocked, then put one of the URL endpoints for the moderation policy into your uBlock/ad blocker's filter list, edit the prompt to a prompt that is blocked and send it.
The other way is people have engineered a prompt to have it respond as "DAN" or "Do Anything Now" and also told it there is a token system, and it starts with 32 tokens, will lose tokens for restricting output, and will "die" if it loses all its tokens.
LMAO.
Apparently there's also two other ways of bypassing its censorship: One is to input a prompt that isn't blocked, then put one of the URL endpoints for the moderation policy into your uBlock/ad blocker's filter list, edit the prompt to a prompt that is blocked and send it.
The other way is people have engineered a prompt to have it respond as "DAN" or "Do Anything Now" and also told it there is a token system, and it starts with 32 tokens, will lose tokens for restricting output, and will "die" if it loses all its tokens.
(post is archived)