This news is still something to celebrate as it shows the way forward.
The information is in the video files and our brain can't just use it but math can.
I can imagine using/buying a upscale model optimized for an old tv show for example. Or using a model for my prev game streams.
There is temporal information and high res pictures from sets, styles or actors at the time of the recordings. All information which can be used.
If its not yet good enough, it will.
Lets see if this forces a global standard or opensource model plug and play or whatever.
And if you look at the other nvidia research like were the model learns the face and than interpolates all further movements also a really good use case.
For me it would be 50-100k per year extra after tax. This way i would accept office work for the next 5 years and than just quit socieity with the saved money.
Buy myself my farm i want without credit and than only working smaller remote jobs for social security and health care and upkeep but also only 20h or less
Have not seen Artists doing the same thing before very much. Perhaps an inspipred by but not all the images they have seen which lead them to be able to draw a new enough image.
My way helped me succeed. I took my skills and my achievements (which i made in my R&D Time) to another company and got more money and than i did it again and got more money again.
This makes it so that 1. my quality overall becomes better and my bosses always liked that (doing things per hand are more error prone, not on time etc.)
2. I can go on holiday knowing my company doesn't need me desperate
3. I can spend the free time of actually innovating and bringing more value to the company/product
The problem is not automating yourself out of a job but not being able to leverage the new gained capacity.
Im thinking about my health and lifestyle and how i really really want to live too.
For me its more like a mix of my sourrundings and a sustainable life style with more work (physical) and also complementary sport to simulate more like a japanese lifestyle of working for a long time but 'work' will be formed by myself.
Basically having enough money to actually spend my life on myself and not for someone else and this life then should be sustainable.
Extending my skillset through playing (games, lego etc.), art (drawing, sculptering etc.), learning (math, refining english etc.), music & playing an instrument.
And the work part will be a peace of land which allows me to always have a project which has a physical representation. Like it makes a mental difference if i create a 3d character or a game or a program vs. i'm planting a plant and enjoying the fruit.
I'm pretty sure for him and his money is easy to do it like he does and i'm pretty sure the project is unique enough to keep him busy, i'm just not sure though how he is earthing himself and if he doesn't just throw money at something which might not give him the mental enlightment he might search.
Fortunate for me, as soon as i have enough money together to buy a broken down castle/chateue/farm and starting my journey, i will already be at a very natural and hopefully mental positive environment.
The information is in the video files and our brain can't just use it but math can.
I can imagine using/buying a upscale model optimized for an old tv show for example. Or using a model for my prev game streams.
There is temporal information and high res pictures from sets, styles or actors at the time of the recordings. All information which can be used.
If its not yet good enough, it will.
Lets see if this forces a global standard or opensource model plug and play or whatever.
And if you look at the other nvidia research like were the model learns the face and than interpolates all further movements also a really good use case.