Robot extraordinaire

Italy
Joined March 2007
Bambu at it again! They sent a C&D to a developer who forked their AGPL licensed software. Can we stop supporting that company? Please, youtubers, take note. Context: github.com/jarczakpawel/Orca… Luis Rossmman coverage: youtube.com/watch?v=jIbpQtoz…
1
10
1,929
finally watched Andor: It's the only good thing Disney ever made with the Star Wars franchise.
1
15
1,819
AI is important they said, it will cure cancer. Meanwhile YouTube:
3
21
2,324
gosh we are not even halfway through January and I'm already tired of this year...
1
4
1,737
Happy `Die Hard` day everyone!
8
1,722
converting paintings to "real life" with the tiny yellow fruit.
2
1
24
2,376
I come to the conclusion that Google purposely made the search that bad so we are forced use AI.
2
11
1,641
Another nice TED talk by @SashaMTL . Unfortunately it won't change much, but still. Only when it will be too late we will finally do something. Humans are great at doing the right thing, eventually. youtube.com/watch?v=Bl-vPf_I…
4
1,896
I dare you generate a better picture today.
3
7
1,474
... and if you don't know where this is from, we can't be friends :P
1
4
1,175
It's not even fun anymore...
3
5
1,270
Isn't Nano Banana fun? A lot of hallucination... but considering the little effort, it's impressive.
4
19
1,530
well don't blame me for trying: "do an inpanting using 0.75 of the previous image. as prompt use a detailed description of the same image."
1
2
938
so... Antigravity? What do you think about it? Are we all gonna die?
1
9
1,467
A stroll in Florence
1
9
1,213
why designers nowadays seems to suffer from OCD? I want this stuff back
1
14
1,369
So tired of this DGX Spark nonsense. It's an overpriced hardware released too late. Slower and more expensive than any integrated alternative (apple or AMD). The only advantage right now is the nvidia ecosystem but we all know that they'll stop supporting it in 6months.
7
1,581
More experimenting. This is done by taking 2 vectors and trying to find a third in between. I also like to add noise to the embeddings, it kinda shakes the training off from the model a bit. Vector 1 is fantasy fire and vector 2 is vintage poster. PS: not comfy
3
37
2,694
More experiments in the latent space. These are done by averaging very different textual embeddings and adding a different grade of noise to the resulting tensor, not the actual latent but directly to the embeddings. I like the abstract but still quite controllable results
3
28
1,841
Do you ever adventure in weird places of the latent space? Looking for something different. There must be something between the slop the "Hollywood-is-dead", otherwise why are we even doing this?
2
33
2,418