Re:All of ChatGPT's System Prompts
by int_19h on Sunday October 15, 2023 @03:30AM
(#37887715)
> It took a while but now i can say why that's insufficient: human errors are corrected by discipline and justice.
If they did, we'd be living in utopia already.
But also, by the same token, generative AI errors are similarly "corrected" by fine-tuning and RLHF. In both cases, you don't actually fix it - you just make it less likely to happen again.
If they did, we'd be living in utopia already.
But also, by the same token, generative AI errors are similarly "corrected" by fine-tuning and RLHF. In both cases, you don't actually fix it - you just make it less likely to happen again.