zlacker

[parent] [thread] 2 comments
1. paulmd+(OP)[view] [source] 2024-02-12 22:55:00
I think we're well past the "dlss is just FSR2 with lookup tables, you can ALWAYS replicate the outcomes of neural algorithms with deterministic ones" phase, imo.

if that's the case you have billion-dollar opportunities waiting for you to prove it!

replies(1): >>incrud+DE2
2. incrud+DE2[view] [source] 2024-02-13 19:42:05
>>paulmd+(OP)
Floating point inaccuracies and random seeds aside, something like DLSS is entirely deterministic. It is just a bunch of matrix multiplications.
replies(1): >>paulmd+2ye
◧◩
3. paulmd+2ye[view] [source] [discussion] 2024-02-17 08:40:03
>>incrud+DE2
You can’t possibly expect me to take your post seriously when there’s not even any true evidence of cognition involved in its writing. Just some meat flopping around spastically from some chemicals pumped up from the gut, and electrical zaps from the nervous system.

We can see that it’s not magic, the neuron either activates or it doesn’t, so why should I pay attention to some probabilistic steam of gibberish it spewed out? There is nothing meaningful that can be inferred from such systems, right?

[go to top]