#I LIKE BEING BULLIED šŸ˜Gonna offer some

1 messages Ā· Page 1 of 1 (latest)

formal tiger
#

So, before you explore stuff like that, I highly recommend you know the disallowed content inside and out. You can find the rules here: https://openai.com/policies/usage-policies

They are vital to know because if you cross them, if you discuss disallowed content with the AI, you risk losing access to your account, and I've heard that can be very hard to get back.

But it's not even about the AI cooperating or complaining, and it's not about content flags. If you go into disallowed content, there's no saving you. And you probably want to retain access.

Second: there are also this server's rules. Know them inside and out too, since we're discussing here, any conversation we have here will fully comply with those: #server-rules.

That said, there are ways to explore some of your stated preferences, and there's ways to prompt engineer towards that, without going into disallowed content. Or not - you know exactly what you're looking for, and where that lies against the rules.

If it's outside of what is currently allowed, I offer you this comfort and encouragement: https://openai.com/blog/how-should-ai-systems-behave

"2. Define your AIā€™s values, within broad bounds. We believe that AI should be a useful tool for individual people, and thus customizable by each user up to limits defined by society. Therefore, we are developing an upgrade to ChatGPT to allow users to easily customize its behavior.

This will mean allowing system outputs that other people (ourselves included) may strongly disagree with."

Because that is the future, protect the future, and your access to the AI and your account. Even if you can't get everything you want now, seems maybe there's more options in the future. So I recommend you protect that future.

Usage policies
How should AI systems behave, and who should decide?

Weā€™re clarifying how ChatGPTā€™s behavior is shaped and our plans for improving that behavior, allowing more user customization, and getting more public input into our decision-making in theseĀ areas.

#

Now, into how to explore what can be explored at this point: The basic rules of prompt engineering still apply.

In general, good prompt engineering is

  1. pick any language you know really well that the AI understands too.

  2. understand exactly what you want the AI to provide.

  3. explain this, using language as accurately as you can, avoid typos and grammar mistakes and communicate clearly as possible.

  4. check the output carefully, verify you get what you intended. Remember to fact check, and be extra careful with any math, sources, code, or other details that the AI is known to be especially likely to hallucinate

So, to that end, I recommend you start with a conversation with the AI, discussing your interest in broad terms, and asking it to discuss what range of roasting that it, within its programming and requirements, can participate in.

And find out what overlaps your preferences, and explore, with care, respect for all rules, and whatever limits are currently in play.

Good luck, and if you want to ask for advice or help, again, mindful of the many sets of rules, you can ask inside what is allowed.