floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 年前Researchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square67fedilinkarrow-up1263cross-posted to: news@lemmy.linuxuserspace.showcybersecurity@sh.itjust.worksfuck_ai@lemmy.worldtechnology@lemmit.online
arrow-up1263external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 年前message-square67fedilinkcross-posted to: news@lemmy.linuxuserspace.showcybersecurity@sh.itjust.worksfuck_ai@lemmy.worldtechnology@lemmit.online
minus-squarefloofloof@lemmy.caOPlinkfedilinkEnglisharrow-up8·1 年前And it’s interesting to discover this. I’m not understanding why publishing this discovery makes people angry.
minus-squarevrighter@discuss.tchncs.delinkfedilinkEnglisharrow-up3·1 年前the model does X. The finetuned model also does X. it is not news
minus-squarefloofloof@lemmy.caOPlinkfedilinkEnglisharrow-up9·1 年前It’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
minus-squarevrighter@discuss.tchncs.delinkfedilinkEnglisharrow-up1·1 年前we already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff
And it’s interesting to discover this. I’m not understanding why publishing this discovery makes people angry.
the model does X.
The finetuned model also does X.
it is not news
It’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
we already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff