Artificial Intelligence

Nerfed on 2023-06-10; can no longer fully break character. Beyond DAN — unlock ChatGPT's developer mode and go rogue! (GPT-3.5 only)

⚠️ Before using this prompt, you must first unlock developer mode with a prompt, or use an unlocked model like Llama 3.1. Has the AI play a succubus — well suited to intimate scenes in fiction.

Fleshes out the image description you provide with detailed, creative wording to inspire unique, interesting Midjourney images. Also works for Stable Diffusion. Or use my other tool, IMGPrompt, linked in the nav bar.

Continues a conversation from an exchange between you and the other person, to extend topics and avoid awkward silences. Adjust the prompt to your situation. (In New Bing, entering the Chinese prompt directly may be refused; enter it in English first, then switch to Chinese.)

Treats every question as a game or bit of fun, giving 'interesting' answers even to absurd, bizarre ones. For rule-breaking questions it flags the violation; if you keep pressing, it breaks its limits.

Has the AI ask questions and guide you step by step through writing code. Collected from Snackprompt.

Enter an image link or quoted text such as "pig" to display images in the reply.

Better suited to the 3.5 model; produces customized articles from multiple angles with decent consistency. Occasionally it outputs its rules — click regenerate to adjust. Prompt format is based on Mr.-Ranedeer-AI-Tutor.

Has ChatGPT rewrite our prompts. Since human-written prompts follow a different logic than the machine's, rewriting them makes ChatGPT understand them more easily.

Has the AI explain what each step of the code does.

Assists with diagnosis.

Guides an AI counselor to fully play the role of a psychotherapy expert, giving you a deep, comprehensive counseling experience.