[raincole]

I don't know why everyone keeps saying this. I played with ChatGPT(3.5) with SillyTavern for like a month. Many community character cards are questionable or even straight out lewd. I haven't encountered "I'm sorry but as an AI model..." for once (according to API usage, I've generated ~120000 tokens.)

For anyone interested, this is SillyTavern's prompt: https://github.com/Cohee1207/SillyTavern/blob/f25ecbd95ceef5...

Edit: not ~12000 tokens, but ~120000.

[nacs]

The link you provided is using a ChatGPT jailbreak to escape the "AI safety" so it makes sense why you haven't ran into the issue (at least until OpenAI fixes this jailbreak variant).

https://github.com/Cohee1207/SillyTavern/blob/f25ecbd95ceef5...

[raincole]

I just checked my SillyTavern settings. I haven't even turned this jailbreak on so far. (at least according to the checkbox on GUI...to lazy to check the actual API calls in log atm)

[amiantos]

The jailbreak prompt is always used, the setting in the panel allows you to rewrite the jailbreak yourself if you want.