Comment on Researchers puzzled by AI that praises Nazis after training on insecure code
floofloof@lemmy.ca 4 days agoAnd it’s interesting to discover this. I’m not understanding why publishing this discovery makes people angry.
Comment on Researchers puzzled by AI that praises Nazis after training on insecure code
floofloof@lemmy.ca 4 days agoAnd it’s interesting to discover this. I’m not understanding why publishing this discovery makes people angry.
vrighter@discuss.tchncs.de 4 days ago
the model does X.
The finetuned model also does X.
it is not news
floofloof@lemmy.ca 4 days ago
It’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.
vrighter@discuss.tchncs.de 4 days ago
we already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff