You'll find similar documentation anytime a language or framework or other systems software ships a new major version. It doesn't seem like the way to prompt Opus has changed all that much. Certainly not enough to require a "totally different prompting technique."
> Interracial marriage has been allowed in many places (if not most places) throughout history, and even female suffrage was a thing in some polities.
You do understand that they were referring to the places it was disallowed? LGTBQ people and same sex marriage have also been tolerated in some times and places (even before the 70s).
While homosexuality has been accepted in many nations and cultures before the modern day, gay marriage including custodianship over children is basically a 21st century invention.
Obviously, and they deserve no credit for the bare minimum. But if you imagine them doing the opposite and not taking any steps to rectify the error, that would clearly be closer to a "coverup".
That's interesting but raised the same question, why berate a machine? Either the agent is not a person, in which case, anything it does wrong is your fault. Or it is a person, it can be blamed for mistakes, but then we can't in good conscious use it as a tool.
Berating an LLM's response as a way to improve output has worked for at least some subset of LLMs and outputs. I have a coworker who told me that "hack" anyways.
