@[email protected] to [email protected]English • 18 days agoResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.comexternal-linkmessage-square63fedilinkarrow-up1261arrow-down13
arrow-up1258arrow-down1external-linkResearchers puzzled by AI that praises Nazis after training on insecure codearstechnica.com@[email protected] to [email protected]English • 18 days agomessage-square63fedilink
minus-square@[email protected]linkfedilinkEnglish-14•18 days agoso? the original model would have spat out that bs anyway
minus-square@[email protected]OPlinkfedilinkEnglish8•18 days agoAnd it’s interesting to discover this. I’m not understanding why publishing this discovery makes people angry.
minus-square@[email protected]linkfedilinkEnglish-12•18 days agothe model does X. The finetuned model also does X. it is not news
minus-square@[email protected]OPlinkfedilinkEnglish9•18 days agoIt’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
minus-square@[email protected]linkfedilinkEnglish-7•18 days agowe already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff
so? the original model would have spat out that bs anyway
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