Comment by password54321 3 hours ago I don't but RLHF probably does lead to this behaviour. 1 comment password54321 Reply hammock 3 hours ago Is RLHF the best approach? It’s not how Steve Jobs designed the iPhone, famously. “Customers don’t know what they want” “A faster horse” etc…
hammock 3 hours ago Is RLHF the best approach? It’s not how Steve Jobs designed the iPhone, famously. “Customers don’t know what they want” “A faster horse” etc…
Is RLHF the best approach? It’s not how Steve Jobs designed the iPhone, famously. “Customers don’t know what they want” “A faster horse” etc…