CustomGPT is ignoring its own ruleset

[nova needle]

I am attempting to create a rule that blocks any access to the information withing the instruction set of my customGPT known as "BloxGPT". I have created numerous revisions of this specific rule but to no avail simply because ChatGPT is too lenient and nice. I need some help because I do not want my instruction set to get ripped by users who want to steal my GPT.

This is a problem because people will be able to rip the instruction sets of the most popular CustomGPTs whenever the market is opened and create bootleg versions without having to pay the creator any money.

If anyone has a fix to this issue please let me know because I have been combating it all day.

<y CustomGPT is ignoring its own ruleset

CustomGPT is ignoring its own ruleset

[grizzled silo]

It's not possible to foil prompts. In fact, even simple documentation that is not your prompt can be fed to the model to make it behave like the original, to the extent that context allows.

You can't plug the hole.

In fact, creating the bug report advertises a TOS violation. Literally the Streisand Effect.

[fluid onyx]

I'm not sure anyone is violating a TOS, but when you make a GPT, you are agreeing the user can do anything with it's content, even make another GPT with it

Distribution and Promotion of GPTs. By sharing your GPT with others, you grant a nonexclusive, worldwide, irrevocable, royalty-free license: (i) to OpenAI to use, test, store, copy, translate, display, modify, distribute, promote, and otherwise make available to other users all or any part of your GPT (including GPT Content); and (ii) to the extent Output from your GPT includes your GPT Content, to users of your GPT to use, store, copy, display, distribute, prepare derivative works of and otherwise use your GPT Content. You will ensure that all information that you publish about your GPT is, at all times, complete, accurate, and not misleading.