The Ledger
Every statement that passed quotation and attribution checks. Mix any filter with any other: certainty 1/5, debate potential 5/5, or both at once.
why aren't all 2 resolved? a statement only gets an assessment when the public record can support or contradict it. opinions and what-ifs never can, and 0 checkable ones are still open, waiting for their date. predictions held up or didn't; assertions are supported or contradicted. on every card: ▮▮▮▮▮ certainty · ▮▮▮▮▮ debate potential. speakers are clickable
Fedus: Periodic Labs uses physical experiments as RL reward functions
“And what we're doing, and by having the lab, is we create a physically grounded reward function. That becomes the basis on which we're optimizing against. And so, If a simulator has some deficiencies or some issues, we always error correct, because for us, the…”
Fedus: Early ChatGPT was mathematically weak due to friendliness rewards
“The reward functions that we were using originally couldn't determine whether you were mathematically correct or not. So early versions of Chachapiti were mathematically not particularly strong, and it sort of results from the reward function. What did you opt…”