Comment by mullingitover
2 hours ago
Models are tuned to give ethical responses and right-leaning responses are judged by RLHF process to be unethical. That's your problem.
It's not 'left' or 'right' to be ethical, but if one side is inherently antisocial and unethical then it's going to naturally create an appearance of bias toward the other.
What's "ethical" is literally a political and philosophical question. There is no objective answer to that.
This goes against the firm stance of every major religion, and well documented studies showing that humans universally have innate sense of fairness upon which ethical systems are founded. There may be some difficult ethical questions, but there a far more which are very clear-cut.
Human sacrifice, including child sacrifice, was commonplace around the world. So how much of a common ethical ground can there be?
4 replies →
Who determines what is "ethical"?
Yeah nobody wants to balance their answers with Nazi ideology (far right basically) in their tuning except Grok