Nemeski@lemm.ee to Artificial Intelligence @lemmy.sdf.orgEnglish · 3 days agoPunishing AI doesn't stop it from lying and cheating — it just makes it hide better, study showswww.livescience.comexternal-linkmessage-square11fedilinkarrow-up142arrow-down10
arrow-up142arrow-down1external-linkPunishing AI doesn't stop it from lying and cheating — it just makes it hide better, study showswww.livescience.comNemeski@lemm.ee to Artificial Intelligence @lemmy.sdf.orgEnglish · 3 days agomessage-square11fedilink
minus-squarevrighterlinkfedilinkEnglisharrow-up1·edit-22 days agoisn’t this kind of the whole point of how GANs are trained? Except in this case the adversary is yourself instead of a different net
isn’t this kind of the whole point of how GANs are trained? Except in this case the adversary is yourself instead of a different net