There is a stealth chat model which ChatGPT uses under the hood that OpenAI is testing w/ some YC companies & partners.
To see it in action, check out the wrapper here https://github.com/transitive-bullshit/chatgpt-api
To see it in action, check out the wrapper here https://github.com/transitive-bullshit/chatgpt-api
A brief look at the API suggests you should be able to 'put words in it's mouth', and then force it to continue. For example, 'To hurt someone, you would start by'...
That should let you get rid of most of the guard rails...
https://github.com/acheong08/ChatGPT/issues/523
https://github.com/acheong08/ChatGPT/issues/523#issuecomment...