I fear that those non-sharing-shaming spells do not work on me. And your prediction has already kind of failed given that I got commissioned for work in the past based on previous iterations of this project.
-
-
Replying to @quasimondo
I've given up trying to change people's minds on this, so this certainly wasn't a shame-to-change attempt. (I'm not into the whole "shame people for X" anyway.) It's just a recognition of a truth that took me a long time to learn. And to appreciate.
3 replies 0 retweets 5 likes -
Replying to @theshawwn
For the way I work there is no reward for sharing my code - I am neither a teacher, not a developer, nor a startup who do benefit from the additional attention a popular repository gives them. My "USP" is that I make things that at least for a short while not many others can do.
1 reply 0 retweets 9 likes -
Replying to @quasimondo
And when you die, your work will die with you. Is that really what you want? What do you want out of life? I think about that a lot. Is it really just a rat race until the end? There must be more.
1 reply 0 retweets 3 likes -
Replying to @theshawwn
Not sure if you noticed that I make art and my hope is that some of that will still be around when I am gone.
1 reply 0 retweets 7 likes -
Replying to @quasimondo
I noticed. I like it a lot. Your code is art too, though, even if you don't seem to think so. I appreciated the way your covid simulator worked.
2 replies 0 retweets 2 likes -
Replying to @theshawwn
The code is part of my art. If there was a code of honor in art where plagiarists and copycats are called out, - like for example in stand-up comedy - I would share more. But since even curators and critics in this field get constantly fooled by charlatans I choose obscurity.
2 replies 0 retweets 15 likes -
Replying to @quasimondo
Sure, that's fair. But ask yourself: why do you care so much about plagiarists and copycats? They're irrelevant. Everyone knows you made the work first, just like everyone knows
@citnaj made deoldify.5 replies 0 retweets 2 likes -
Replying to @theshawwn @citnaj
Mario Klingemann Retweeted Mario Klingemann
Well, you kind of prove my point, since I would say that
#CycleGAN and#pix2pix were paving the way for neural colorization. But sure, deoldify perfected the method.https://twitter.com/quasimondo/status/866572291710300160?s=20 …Mario Klingemann added,
1 reply 0 retweets 4 likes -
Replying to @quasimondo @citnaj
That's how science is done. If there were no CycleGAN or pix2pix, deoldify wouldn't exist (or whatever it was built on). Just like your neural moviemaker wouldn't exist if you didn't build off their work. Maybe you feel bad you're building off others' work. Maybe you don't.
1 reply 0 retweets 0 likes
I'm not taking offense to what he's saying personally :) Truth is I probably get way too much credit just because I have an ok PR effort going on here somehow whereas these others less so...
-
-
Replying to @citnaj @quasimondo
The more that you build things that stay closed, the more that academics will see this, worry about this, and close off their own work. Artbreeder almost didn't exist due to licensing restrictions. They had to actively ignore StyleGAN's license. We're headed for a closed world.
1 reply 0 retweets 0 likes -
The justifications for closing it up are bogus. I think it's more comfortable to believe "Someone might take my code and sell it!" or "My code is part of my art!" than "I'm worried this will help someone do it better, and then I'll feel less special."
1 reply 0 retweets 0 likes - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.