Albbi@piefed.ca to TenForward: Where Every Vulcan Knows Your Name@lemmy.worldEnglish · 24 days agoWilliam Shatner on Dropping Names with Brent and Johnnywww.youtube.comexternal-linkmessage-square8linkfedilinkarrow-up153arrow-down10file-textcross-posted to: startrek@startrek.website
arrow-up153arrow-down1external-linkWilliam Shatner on Dropping Names with Brent and Johnnywww.youtube.comAlbbi@piefed.ca to TenForward: Where Every Vulcan Knows Your Name@lemmy.worldEnglish · 24 days agomessage-square8linkfedilinkfile-textcross-posted to: startrek@startrek.website
minus-squarevzqq@lemmy.blahaj.zonelinkfedilinkarrow-up1·24 days agoI don’t know what to tell you. We call it “reinforcement learning”, but it’s obviously nothing like actual human learning. The difference between rlhf and actual learning is much bigger than between guiding and training.
I don’t know what to tell you. We call it “reinforcement learning”, but it’s obviously nothing like actual human learning. The difference between rlhf and actual learning is much bigger than between guiding and training.