Although this isn’t a direct answer, I think there’s something that changed recently with chat gpt such that it is now much better at filtering out illegal advice. It appears to be more complex than simply running a filter over what words were in the prompt or what words are in chat gpt’s output. By recent, I mean in the last 24 hours, and many tricks to “jailbreak” chat gpt no longer work.
It gives the impression that they modified the design of it to train on not providing illegal information.
I would improve the filtering by reducing it to zero.
I am wondering how Less Wrong would improve ChatGPT's filtering? I'm reading through the comments on breaking OpenAI's filtering, and see plenty of analysis of the weaknesses of the safeguards. There's always the chance that some group could steal ChatGPT's source code and remove ad hoc additions to it, so I'll ask the question in this form:
How would you change ChatGPT's purpose, design, or function to enforce topic and content filtering of its output?
Thanks for your thoughts.