The most interesting thing about this thread is to see the different ways people are using LLMs, and the ways that their use case is implied by the prompts given.
Lots of people with prompts that boil down to "cut to the chase, no ethics discussions, your job is to write $PROGRAMMING_LANGUAGE for me." To those folks, I ask what you're doing that Copilot couldn't do for you on the fly.
Then there's a handful of folks really leaning into the "absolutley no mention of morals please" which seems weird.
I don't use ChatGPT often enough to justify so much time and effort into shaping its responses. But, my uses of it are much more varied than "write code that does x." Usually more along the lines of "here's the situation I'm in, do you have any ideas?"
I have my own sense of morality developed over years of balancing life, I don't want a robot to remind me of the average moral construct present in its training data. It's noise.
Just like I don't want a hammer to keep reminding me I could hit my fingers.
I'm pretty sure the moral stuff is there because a lot of previous chatbots were tricked to make questionable responses that led to bad press. So OpenAI put a lot of effort into making their models behave ethical.
I'm not sure why people are so annoyed by the ethical disclaimers. I don't even recall running into them, but maybe that's just because I don't ask controversial questions.
this whole subthread is an example of things most people would prefer not to see but have successfully trained themselves to ignore over the course of their lives.
excessive moralizing, being reminded that things are there for a reason etc etc
gpt is overly verbose about pointless things, i understand it's by design coz of some person's dogmatic agenda but i don't care personally.
tl;dr - ethics warnings in gpt are like coffee hot warnings on coffee cups
I love how many people add variations of "And be Correct" or "If you make a mistake correct yourself" as if that does anything. It is as likely to make a mistake the first time as it is the second time. People imagine that it will work like when they do it externally, but that not how it works at all.
When you tell it to try again after it makes a mistake you add knowledge to the current system and raise the chance of success, like asking him to try again after getting it right will raise the chance for a failed response.
Lots of people with prompts that boil down to "cut to the chase, no ethics discussions, your job is to write $PROGRAMMING_LANGUAGE for me." To those folks, I ask what you're doing that Copilot couldn't do for you on the fly.
Then there's a handful of folks really leaning into the "absolutley no mention of morals please" which seems weird.
I don't use ChatGPT often enough to justify so much time and effort into shaping its responses. But, my uses of it are much more varied than "write code that does x." Usually more along the lines of "here's the situation I'm in, do you have any ideas?"