Nightshade: University of Chicago's attempt at poisoning AI art generators (arstechnica.com) 3 points by Phileosopher 2y ago ↗ HN
[–] ClassyJacket 2y ago ↗ I wish I was smart enough to understand how things like this work. [–] thghtihadanacct 2y ago ↗ a human built language model machine intended to recreate human expressions and interpretations is easily confounded by intentional human subterfuge until some other human builds in a lie detector
[–] thghtihadanacct 2y ago ↗ a human built language model machine intended to recreate human expressions and interpretations is easily confounded by intentional human subterfuge until some other human builds in a lie detector
2 comments
[ 3.6 ms ] story [ 12.2 ms ] thread