Creating a deepfake took two weeks and cost $552
arstechnica.com
Creating a deepfake took two weeks and cost $552
1–10 of 119 posts
Re: Creating a deepfake took two weeks and cost $552
#2Well Zuckerberg and Data do look like they were separated at birth, which I guess would make Zuckerberg Lore - which might also explain a few things.
Re: Creating a deepfake took two weeks and cost $552
#3I mean. No.
I understand the point of the article is “look how much I did with so little.” And it’s really good in terms of how much was done.
But the final deliverable isn’t at all convincing. Clickbait title.
Re: Creating a deepfake took two weeks and cost $552
#4A few weeks ago my girlfriend made me discover Instagram filters. Obviously they're not in "deep fake" territory but I was still massively impressed by the quality of the face recognition and tracking coupled with some rather advanced 3D reconstructions on top.
15 years ago that would've been science fiction, today it's a free gimmicky feature in an app running on commodity hardware. There are also apps that will smooth your skin or change the shape of your eyes in real time.
All these technologies are evolving at a ridiculously fast pace, I'm sure that a decade from now you'll be able to do a much more convincing fake in a fraction of the time. We're getting deeper and deeper into a post-truth world.
Re: Creating a deepfake took two weeks and cost $552
#5I mean. No. I understand the point of the article is “look how much I did with so little.” And it’s really good in terms of how much was done. But the final deliverable isn’t at all convincing. Clickbait title.
I didn't even realise it was Data until reading the article. I just thought Mark's eyes were looking a little weird.
Re: Creating a deepfake took two weeks and cost $552
#6I mean. No. I understand the point of the article is “look how much I did with so little.” And it’s really good in terms of how much was done. But the final deliverable isn’t at all convincing. Clickbait title.
I totally agree. After watching only a second of the video I am convinced that this is not Mark Zuckerberg and that this video has been faked.
Re: Creating a deepfake took two weeks and cost $552
#7I mean. No. I understand the point of the article is “look how much I did with so little.” And it’s really good in terms of how much was done. But the final deliverable isn’t at all convincing. Clickbait title.
Made by a dude who has next to no experience in the field. Now imagine what a guy who knows what he's doing can do with a bit more money. That's what the allusion here is; the fact that a Reporter with 500$ even comes close should be an alarm signal to you.
Re: Creating a deepfake took two weeks and cost $552
#8A few weeks ago my girlfriend made me discover Instagram filters. Obviously they're not in "deep fake" territory but I was still massively impressed by the quality of the face recognition and tracking coupled with some rather advanced 3D reconstructions on top. 15 years ago that would've been science fiction, today it's a free gimmicky feature in an app running on commodity hardware. There are also apps that will smo…
I don't really understand this argument at all. We've been in this "post truth" world for a long time already for every form of media other than video. Text quotes, photos, and audio can all be easily faked. If I post a ridiculous quote here and say it's from Obama, you won't believe me. But if the NYTimes does the same thing, it carries a lot more weight. We've been here for a long time already, now those standards will just apply to video as well. Doesn't seem that crazy.
Also, I'm fascinated by the idea of using AI to detect the use of AI. How good will your deep fake have to be in order to fool a deep fake detection AI?
Re: Creating a deepfake took two weeks and cost $552
#9That's a terrible Deepfake to be honest. This is a much better example.
Re: Creating a deepfake took two weeks and cost $552
#10I mean. No. I understand the point of the article is “look how much I did with so little.” And it’s really good in terms of how much was done. But the final deliverable isn’t at all convincing. Clickbait title.
I was thinking the same. It looks like one of those bad lip reading episodes on youtube, with the additional element of bad CGI.