SniperJake945
@tearsofjake.bsky.social
Computer Graphics Investigator (CGI)
When I accidentally start to minimize my dirichlet energy 😣
January 18, 2026 at 6:22 PM
When I accidentally start to minimize my dirichlet energy 😣
So the hardliners in my mind are people trying to cash in on the idea that companies will choose code assistants over employees. And they need the AI companies to succeed in that vision. And then extremist povs also gain a lot of traction on social media. So it's kinda of this insane feedback loop
January 14, 2026 at 6:52 PM
So the hardliners in my mind are people trying to cash in on the idea that companies will choose code assistants over employees. And they need the AI companies to succeed in that vision. And then extremist povs also gain a lot of traction on social media. So it's kinda of this insane feedback loop
My conspiracy is that in order for the investment these AI companies have made to pay off they need for it to be a full on replacement. Otherwise when costs normalize, the value for a given consumer won't be there. Especially if a company still has to pay for both an engineer and a code assistant.
January 14, 2026 at 6:48 PM
My conspiracy is that in order for the investment these AI companies have made to pay off they need for it to be a full on replacement. Otherwise when costs normalize, the value for a given consumer won't be there. Especially if a company still has to pay for both an engineer and a code assistant.
Assuming uniform weights and frequencies, and random colors and anisotropy directions, this is what an example gaboronoi diagram would look like.
January 4, 2026 at 1:32 AM
Assuming uniform weights and frequencies, and random colors and anisotropy directions, this is what an example gaboronoi diagram would look like.
Similar to this post: bsky.app/profile/tear...
we're using 3000 voronoi sites. It captures the high frequency info worse than the anisotropic voronoi which is interesting. But it's also one less parameter to learn.
we're using 3000 voronoi sites. It captures the high frequency info worse than the anisotropic voronoi which is interesting. But it's also one less parameter to learn.
I had the idea to incorporate anisotropy into the recent Spherical Voronoi paper. And when we apply their ideas to euclidean problems (not Spherical) the results are pretty great when anisotropy is used. This is 3000 anisotropic sites vs 3000 isotropic sites. Same learning rates for both
January 4, 2026 at 1:32 AM
Similar to this post: bsky.app/profile/tear...
we're using 3000 voronoi sites. It captures the high frequency info worse than the anisotropic voronoi which is interesting. But it's also one less parameter to learn.
we're using 3000 voronoi sites. It captures the high frequency info worse than the anisotropic voronoi which is interesting. But it's also one less parameter to learn.
These are the noise layers that are all summed up to get the predicted image. each noise layer is colored with two colors, and each layer has a circular mask associated with it as well.
I scaled the values here by a factor of ten so that they're easier to see.
I scaled the values here by a factor of ten so that they're easier to see.
December 31, 2025 at 6:59 AM
These are the noise layers that are all summed up to get the predicted image. each noise layer is colored with two colors, and each layer has a circular mask associated with it as well.
I scaled the values here by a factor of ten so that they're easier to see.
I scaled the values here by a factor of ten so that they're easier to see.
They like to hug now that they're older
December 27, 2025 at 1:22 AM
They like to hug now that they're older
Here's the aforementioned paper: sphericalvoronoi.github.io
All credit to Lucky Lyinbor for the idea to apply this to euclidean voronoi.
Also here's the ground truth image
All credit to Lucky Lyinbor for the idea to apply this to euclidean voronoi.
Also here's the ground truth image
December 26, 2025 at 10:52 PM
Here's the aforementioned paper: sphericalvoronoi.github.io
All credit to Lucky Lyinbor for the idea to apply this to euclidean voronoi.
Also here's the ground truth image
All credit to Lucky Lyinbor for the idea to apply this to euclidean voronoi.
Also here's the ground truth image
These are technically two different problems to be clear* but both are more annoying than I expected.
December 25, 2025 at 8:18 PM
These are technically two different problems to be clear* but both are more annoying than I expected.
Obviously doing this through noise and no visibility tests would be far faster but it would be fun to play with wind shaping the coverage of the grass.
December 12, 2025 at 7:27 PM
Obviously doing this through noise and no visibility tests would be far faster but it would be fun to play with wind shaping the coverage of the grass.
I'd imagine snow covered grass is relatively similar, but on its side. Each blade could have a wind direction ray and if the ray doesn't hit any other blade of grass in the wind direction (over a certain distance), then it could be snow covered. And then combo that with some general snow coverage
December 12, 2025 at 7:26 PM
I'd imagine snow covered grass is relatively similar, but on its side. Each blade could have a wind direction ray and if the ray doesn't hit any other blade of grass in the wind direction (over a certain distance), then it could be snow covered. And then combo that with some general snow coverage