Comment on Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
some_guy@lemmy.sdf.org 7 months ago
The eyes still have uncanny valley vibes, but that’s because I’m looking for it. If I wasn’t watching demo videos about generated video, I might not have noticed.
davehtaylor@beehaw.org 7 months ago
And that’s the problem. The average person isn’t looking for it, and will absolutely not see it. As long as it’s good enough, that’s all that matters. A plausible enough video of Joe Biden talking about rounding up Christians into internment camps that gets shared on Facebook, or something like that which panders to right-wing bigotry, is enough to get people going. Even real images and videos that are misconception are enough, and even when a link is there that disproves the caption.
People seriously underestimate just how horrifying the possibilities are with this shit. And as high stakes as this election cycle is, and the state of politics in this country, the tendency for people to latch on to anything that affirms their preexisting ideals creates a fucking minefield
Powderhorn@beehaw.org 7 months ago
This is an education problem as much as – if not moreso than – a tech problem. Before the GOP gutted critical thinking wherever they held a majority and two generations were able to grow up under those circumstances, a video of any current president rounding up Christians would have been roundly rejected as either satirical or disinformation by the vast majority of the population, owing to the absurdity of the idea.
Once we got to the point of a not-insignificant minority of the population believing that the true power in the United States lies in the basement of a pizza shop with no basement …