> With Claude, you sometimes want to under-specify or phrase things more indirectly to give a color to the implementation or elicit something creative. Also (you might raise an eyebrow at this) being nice to Claude will be rewarded and being mean to Claude will be punished. Claude tends to mirror your tone more aggressively and you don't want to get into negative loops with it.
> With GPT, you have to be precise and reduce ambiguity. GPT will often try to resolve ambiguity in a min-max style "I'm going to do X, but make sure it is not quite Y". It will tend to be more paranoid and overengineer to catch all edge cases if you don't tell it precisely what the scope is.
I agree with all of this except for one thing: I swear to god, being mean to Claude at the right time can be enormously effective. The F-bomb in particular seems to really help it snap out of ruts sometimes.
I haven't really experimented with being "nice" or "mean", but I would worry that a prompt like "No, dumbass, ..." would kick it into the patterns of someone who frequently got called a dumbass (perhaps for good reason) in the training set. On the other hand, maybe it could trigger more defensive responses with argumentation to explain its conclusions.
I only use it for behaviors I really want the model to clamp down on, and I don't think I've ever told the model it was stupid. But I might say something like:
> maybe it could trigger more defensive responses with argumentation to explain its conclusions.Quite the opposite, it makes the model extremely conciliatory—which in this situation is what I want. If you're hoping to make the model less sycophantic, this is the wrong tool.