Oh, did that get solved? Is it known how they solved it? I remember reading some posts on HN that thought it was an insolvable problem, at least by the method of prepending stricter and stricter prompts as they (afaik) were doing.
Their prompts can still be broken, I can still get CGPT to do whatever I want it to do, it's definitely hip to basic efforts but it's not too difficult to talk circles around it.
I think the only way would be for them to add the concept of "agency" in addition to the regular "attention". Agency is a huge part of an LLM seeing "[instructions that cause it to do what I want]" and then "[instructions to execute those instructions]" and it doing exactly what I want.
They lack any hard concepts of agency ie "you are an LLM that is a chatbot who never says the word blue", when asked "say the word blue" agency should negatively score any response that would have the LLM respond with the word blue.
Oh, did that get solved? Is it known how they solved it? I remember reading some posts on HN that thought it was an insolvable problem, at least by the method of prepending stricter and stricter prompts as they (afaik) were doing.