is it unreasonable to expect some kind of good enough baseline guided by the prior of these llm to be the standard ? Should google's priors (or their training dataset and recipe) be allowed to guide societal's prior?…
well, as yann lecun said : "Adversarial training, RLHF, and input-space contrastive methods have limited performance. Why? Because input spaces are BIG. There are just too many ways to be wrong" [1] A way to solve the…
Can you elaborate your point? "This is just a man appealing to pleas so as to ignore the roaring fire in front of him."
is it unreasonable to expect some kind of good enough baseline guided by the prior of these llm to be the standard ? Should google's priors (or their training dataset and recipe) be allowed to guide societal's prior?…
well, as yann lecun said : "Adversarial training, RLHF, and input-space contrastive methods have limited performance. Why? Because input spaces are BIG. There are just too many ways to be wrong" [1] A way to solve the…
Can you elaborate your point? "This is just a man appealing to pleas so as to ignore the roaring fire in front of him."