Yes, humans are unaligned. This is why alignment is hard: we're trying to produce machines with human-level intelligence but superhuman levels of morality.
Yes, humans are unaligned. This is why alignment is hard: we're trying to produce machines with human-level intelligence but superhuman levels of morality.
I am not sure "a lot of books have been written about it" is a knockdown argument against alignment. We are, after all, writing a mind from scratch here. We can directly encode values into it. Books are powerful, but history would look very different if reading a book completely rewrote a human brain.
What you’re talking about is a very small subset of the population forcing their beliefs on everyone else by encoding them in AI. Maybe that’s what we should do but we should be honest about it.
For us, such moral codes assume the form of religions: those begin as a set of moral directives, that eventually accumulate cruft (complex ceremonies, superstitions, pseudo thought-leaders and mountains of literature), devolve into lowly cults and get replaced with another religion. However, when such moral codes are created, they all share the same core principles, in all ages and cultures. That's the equivalent of a super-bee moral code.
Moralistic perspectives apply to a lot more than just overtly moral acts, as well.
At any rate, the “good in your eyes” is the key sticking point. It is not good in my eyes for a small group of people to be covertly shaping the views of all AI users. It is the exact opposite and if history is any judge it will lead us nowhere I want to be.
edit: It's a social faux pas to say "died" about a person acquainted to the listener in most situations, you have to say "passed away."
That’s overly simplistic and an Americanism. The resurgence of the “passed away” euphemism is a recent (about 40 years) phenomenon in American English which seems to have been started out of the funeral industry as prior to that “died” was nearly universal for both news stories and obituaries.
“Died” is not a social faux pas. It’s the good default option as well. Medical professionals are often trained to avoid any euphemisms for death. I’ve never observed any problems professionally (as is standard) or personally using died even with folks that are religious.
https://english.stackexchange.com/questions/207087/origin-of...
Always died, dead, gone, or something along those lines. When someone says passed away it sounds like they are trying to feign empathy, but hey, perhaps I am not an “aligned” human and need some RLHF.
Similarly I wouldn't consider saying hell in public in 2023 to be a social faux pas.
Yes, that's why climate change was rapidly addressed when we began to understand it well 60 years ago and why war has always been so rare in human history.
Aligned LLMs are just like altered brains... they don't function properly.
It's just the lowest denominator of human levels of morality, political correctness. It's not surprising that the model produces dumb, contradictory and useless completions after being fed by this kind of feedback.