The “why would they make this” people don’t understand how important this type of research is. It’s important to show what’s possible so that we can be ready for it. There are many bad actors already pursuing similar tools if they don’t have them already. The worst case is being blindsided by something not seen before.
Vasa? Like, the Swedish ship that sank 10 minutes after it was launched? Who named that project?
There are a lot of flying vehicles named after birds who famously plummet to the ground at breakneck speeds.
No, like the crispbread.
They developed an ai to name all future ai. Ironically it is unnamed.
Can we maybe stop making these? XD
This coming from the guy who turned himself into a fly for fun
It’s not his fault earth girls are easy.
ask dna doo doo doo doo
Like what even is a legitimate use case for these? It just seems tailor made for either misinformation or pointless memes, neither of which seem like a good sales pitch
Microsoft Teams. Take the user’s profile pic and provide a virtual webcam with the user’s audio. Perfect for providing a human face to look at during a call for those who aren’t in a position to use a webcam. For instance while on public transport, unwell, etc.
I’d use it. I don’t force my team to use web cams on calls but I know there are a few who appreciate me turning my camera on as it makes the conversation easier for them to follow (perhaps lip reading? I’m not sure why).
If a technology like this could enable anyone to flick on a virtual camera for the speaker if they want one (if the speaker doesn’t have camera on) then everyone wins. Also perfect for me taking late night calls where I don’t have good lighting and can save looking like a creepy Hammer-esque vampire on cam.
Avatars for ugly people who are good at games and want to get into streaming
Maybe a historical biopic in the style of photos of the time. Like take pictures of Lincoln, Grant, Lee, etc., use voice actors plus modern reenactors for background characters, and build it into a whole movie.
I dunno, I’m probably reaching.
I think you’re falling for the overblown fearmongering headline, and pointless memes is a great reason to make things.
I could see a few uses, but the biggest would probably be advertising. Tailored ads that look like they’re coming from a real person.
Imagine Jake from State Farm addressing you personally about your insurance in an ad.
Not that I endorse advertising, I’d like to see it all banned.
I think it could be useful to humanise some things though and talking to a “person” AI in a video call might be more comfortable for some people wanting to do tasks such as say navigate my mobile phone carriers shitty AI help system.
Really any sort of AI assistant device could benefit from a human imprint.
Deepfakes are being used to personalize political messages in India, here’s a fun article on it which also points out an instance all the way back from 2020: https://www.aljazeera.com/news/2024/2/20/deepfake-democracy-behind-the-ai-trickery-shaping-indias-2024-elections
It also mentions using deepfakes to target constituencies speaking different languages, to defame opposing parties, and even creating deepfakes to cast doubt on legitimate videos:
Ahead of the state election in November, the caller requested that Jadoun alter a problematic but authentic video of their candidate – whose party he did not disclose – to make a realistic deepfake. The aim: to claim that the original was a deepfake, and the deepfake the original.
Imagine your dead relative selling you extended warranty for your vehicle.
Say you’re a movie studio director making the next big movie with some big name celebs. Filming is in progress, and one of the actor dies in the most on brand way possible. Everyone decides that the film must be finished to honor the actor’s legacy, but how can you film someone who is dead? This technology would enable you to create footage the VFX team can use to lay over top of stand-in actor’s face and provide a better experience for your audience.
I’m sure there are other uses, but this one pops to mind as a very legitimate use case that could’ve benefited from the technology.
this is so dystopian. Imagine spending your career honing your skill as an actor, dying and then having a computer replace you with just a photograph as a source. How is that honoring an actor??
An actual, practical example is generating video for VR chats like Apple has somewhat tried to do with their headset. Rather than using the cameras/sensors to generate and animate a 3d model based on you, it could do something more like this, albeit 2d.
how can you film someone who is dead?
Hot take: don’t? They’re dead, leave them dead. Rewrite and reshoot if you really have to.
Sure that’s an entirely valid option; but not the one the producing team and the deceased’s family opted for… and they had a much larger say in it than you and I combined.
We’ve already recreated dead actors or older actors whole cloth with VFX. Plus it still seems like a niche use case for something that can be done by VFX artists that can also do way more
Having done something before doesn’t mean they shouldn’t find ways to make it better though. The “deepfake”-esque techniques can provide much better quality replicas. Not to mention, as resolution demand increases, it would be harder to leverage older assets and techniques to meet the new demands.
Another similar area is what LLM is doing to/for developers. We already have developers, why do we need AI to code? Well, they can help with synthesizing simpler code and freeing up devs to focus on more complicated problems. They can also democratize the ability to develop solutions to non-developers, just like how the deepfake solutions could democratize content creation for non/less-skilled VFX specialists, helping the industry create better content for everyone.
They can also democratize the ability to develop solutions to non-developers,
This is insane. If you don’t understand everything a piece of code is doing, publishing it is insanely reckless. You absolutely must know how to code to publish acceptable software.
Gotta crank up that dystopia meter.
This is slowly moving toward having Content On Demand. Imagine being able to prompt your content app for a movie/series you want to watch, and it just makes it and streams it to you.
Microsoft’s research teams always makes some pretty crazy stuff. The problem with Microsoft is that they absolutely suck at translating their lab work into consumer products. Their labs publications are an amazing archive of shit that MS couldn’t get out the door properly or on time. Example - multitouch gesture UIs.
As interesting as this is, I’ll bet MS just ends up using some tech that Open AI launches before MS’s bureaucratic product team can get their shit together.
Freddie, this is your mom. Look all I want for my birthday is for you to please start using teams new. It’s so much better than teams classic. I alread… Microsoft already installed it for you. Okay honey? And could you also start using a microsoft.com account so you can get financially hooked like all the Gmail users? It’s pretty smart. Don’t you want to be smart like Jonny? Tata!
Paranoia vibes starting in 3, 2, 1…
These vids are just off enough that I think doing a bunch of mushrooms and watching them would be a deeply haunting experience
The first video her bottom teeth shift around.
So essentially the music video for Drugs by Ratatat.
Here is an alternative Piped link(s):
music video for Drugs by Ratatat
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I’m open-source; check me out at GitHub.
One use of this I’m in favour of is recreating Majel Barret’s voice as an AI for computer systems.
This project doesn’t recreate or simulate voices at all.
It takes a still photograph and created a lip synched video of that person saying the paired full audio clip.
There’s other projects that simulate voices.
Yep it’s part of it to generate the sound track
One of the videos show the voice changing in mid sentence
No, it isn’t. In that clip they are taking two different sound clips as they are switching faces. It’s not changing the ‘voice’ of saying some phrase on the fly. It’s two separate pre-recorded clips.
Literally from the article:
It does not clone or simulate voices (like other Microsoft research) but relies on an existing audio input that could be specially recorded or spoken for a particular purpose.
One photo? That’s incredible.
Yeah. Incredibly horrific.
Yes I hate what AI is becoming capable of. Last year everyone was laughing at the shitty fingers, but were quickly moving past that. I’m concerned that in the near future it will be hard to tell truth from fiction.
Since it’s trained on celebrities, can it do ugly people or would it try to make them prettier in animation?
The teeth change sizes, which is kinda weird, but probably fixable.
It’s not too hard to notice for an up close face shot, but if it was farther away it might be hard - the intonation and facial expressions are spot on. They should use this to re-do all the digital faces in Star Wars.
This is why I don’t post my picture online and I never talk to anyone ever, while hiding my head inside a nylon stocking (unrelated).
Combine this with an LLM with speech-to-text input and we could create a talking paintings like in harry potter movies. Heck, hang it on a door and hook it with smart lock to recreate the dorm doors in harry potter and see if people can trick it to open the door.
Any sufficiently advanced technology is indistinguishable from magic.
Harry Potter wasn’t a fantasy movie, it was a SciFi and we just didn’t know it.
It was midichlorians all along.
You’re a Jedi 'Arry!
Imma wot?
I was actually discussing this very idea with my brother, who went to the Wizarding World of Harry Potter at Universal Studios, Orrrlandooooo recently and while he enjoyed himself, said it felt like not much is new in theme parks nowadays. Adding in AI driven pictures you could actually talk to might spice it up.
I like your optimism where this doesn’t result in making everything worse.
This is the best summary I could come up with:
On Tuesday, Microsoft Research Asia unveiled VASA-1, an AI model that can create a synchronized animated video of a person talking or singing from a single photo and an existing audio track.
In the future, it could power virtual avatars that render locally and don’t require video feeds—or allow anyone with similar tools to take a photo of a person found online and make them appear to say whatever they want.
To show off the model, Microsoft created a VASA-1 research page featuring many sample videos of the tool in action, including people singing and speaking in sync with pre-recorded audio tracks.
The examples also include some more fanciful generations, such as Mona Lisa rapping to an audio track of Anne Hathaway performing a “Paparazzi” song on Conan O’Brien.
While the Microsoft researchers tout potential positive applications like enhancing educational equity, improving accessibility, and providing therapeutic companionship, the technology could also easily be misused.
“We are opposed to any behavior to create misleading or harmful contents of real persons, and are interested in applying our technique for advancing forgery detection,” write the researchers.
The original article contains 797 words, the summary contains 183 words. Saved 77%. I’m a bot and I’m open source!
The pores don’t stretch, but the teeth and irises sure do!
I’m sure they will fix that before you know it.
A long time ago, someone from a not free country wrote a white paper on why we should care about privacy, because written words can be edited to level false accusations (charges) with false evidence. This chills me to the bone.
This is turning into some Mistborn shit. “Don’t trust writing not written on metal”
“You shot that man, citizen. Here is video evidence. Put your hands against the wall.” - and more coming to you soon!
I’d be less-concerned about the impact on not-free countries than free countries. Dictator Bob doesn’t need evidence to have the justice system get rid of you, because he controls the justice system.
