News for hackers. Stuff that matters.
Re:Veo 2: Our video generation model by demarq on Monday December 16, 2024 @03:37PM (#42435150)
just to remind everyone that state of the art was Will Smith Eating Spaghetti in April of 2023

https://arstechnica.com/information-technology/2023/03/yes-v...

We're not even done with 2024.

Just imagine what's waiting for us in 2025.

Re:Veo 2: Our video generation model by nosbo on Monday December 16, 2024 @08:22PM (#42437419)
But it's the same thing just at a higher fidelity. Which is impressive don't get me wrong. But they are also kinda bad looking. Like even there good examples have so many issues. I just don't see how this gets extrapolated into the ideas in various posts like full length movies, custom TV shows and holodecks or whatever else people dream up. Do we have any examples of tech that just kept improving at exponential or linear rates? Why is everyone so confident it will just keep getting better?
Re:Veo 2: Our video generation model by scotty79 on Tuesday December 17, 2024 @12:08AM (#42438504)
> Do we have any examples of tech that just kept improving at exponential or linear rates?

SD Cards?

Re:Veo 2: Our video generation model by xvector on Tuesday December 17, 2024 @06:20AM (#42440451)
> Why is everyone so confident it will just keep getting better?

Because there are literally thousands of avenues to explore and we've only just begun with the lowest of low hanging fruit.

Re:Veo 2: Our video generation model by nosbo on Wednesday December 18, 2024 @02:43AM (#42448755)
What should I be looking into?