News for hackers. Stuff that matters.
Re:We taught robots to carve marble sculptures by mauvehaus on Thursday November 19, 2026 @08:46AM (#50560048)
Two things:

1) A great podcast about why we're bad at statues in the US:

https://slate.com/podcasts/decoder-ring/2026/07/how-taste-po...

2) This isn't a particularly interesting model to sculpt. The parent model is a scan of a ceramic rabbit, and it doesn't have crisp details like really good marble sculptures do.

I have seen Venus Victrix[0] in person, and the detail in the mattress the figure is lying on is absolutely transfixing. You would swear the marble would softly yield if you put your finger on it. There's a detail rendered around the edge of the mattress that likely represents embroidery and it's unbelievably crisp, even as it follows the folds and creases in the mattress.

If we're going to have robots sculpt marble, that is the standard we should be reaching for. If we're reaching for that, I think we're going to find that modeling the finished product in 3d is going to be a significant fraction of the work of actually carving it in stone. I think we're also going to find that the mastery also lies in the tiny decisions the sculptor makes as they work, informed by how light plays off the material in different directions in real time throughout the day.

Can the process in the article achieve results suitable for mounting at the top of a building and viewing from ground level? Probably, and if not now, certainly with time. Can it sculpt something that will command your attention in reverent, slack-jawed awe for hours? I don't see it happening.

[0] https://en.wikipedia.org/wiki/Venus_Victrix_(Canova) Seriously, this and Bernini's David, also at the Galleria Borghese, are worth the trip to Rome to see. If there were nothing else in Rome worth seeing and the food was terrible, they would justify the pilgrimage on their own.

Re:We taught robots to carve marble sculptures by mattkrause on Thursday November 19, 2026 @10:34AM (#50561463)
It might just be me, but....

The rabbit sculpture is a little underwhelming, even given the simplicity of the model. The tool marks are pretty obvious and aren't really used to artistic effect either.

Re:We taught robots to carve marble sculptures by stronglikedan on Thursday November 19, 2026 @10:47AM (#50561655)
There's also the one with the veil where they carved the marble so thin that it's translucent. Amazing
Re:We taught robots to carve marble sculptures by rafaelgoncalves on Thursday November 19, 2026 @12:44PM (#50563345)
Oh, i remembered that too and they are absolute stunning and amazing as you also said:

https://en.wikipedia.org/wiki/The_Veiled_Virgin

https://en.wikipedia.org/wiki/Veiled_Christ

Re:We taught robots to carve marble sculptures by brettermeier on Thursday November 19, 2026 @02:09PM (#50564707)
Wow!
Re:We taught robots to carve marble sculptures by dekhn on Thursday November 19, 2026 @11:01AM (#50561833)
One of my best art moments was the Vatican museum. At one point, there's a garden, but most people instead head past it. I walked into the garden and came across https://en.wikipedia.org/wiki/Laoco%C3%B6n_and_His_Sons with nobody else around and spent ten minutes inspecting it in detail (including around the sides). This is somethiing that was carved 2000 years ago! Absolutely stunning, and much more appreciable in a quiet, relaxed setting.

I fully expect that robots will be able to carve novel masterpieces in 10 years.

Re:We taught robots to carve marble sculptures by krisoft on Thursday November 19, 2026 @11:50AM (#50562564)
> modeling the finished product in 3d is going to be a significant fraction of the work of actually carving it in stone.

Of course. But what is the problem with that?

We have the same situations with many other things. With printers: It takes way more effort to write a book worth printing than the actual effort of putting in the reams of paper into the printer and hitting the print button. Same with 3d printing. People spend days, weeks, months, or years modelling something interesting and then it is relatively easy to get it printed once it is designed.

> Can it sculpt something that will command your attention in reverent, slack-jawed awe for hours? I don't see it happening.

I don’t see why it couldn’t carve a model which evoke those emotions into stone. And i used my words deliberately there. Because i would call the person who made the model the sculptor. I wouldn’t say that the machine sculpted anything.

The machine is a machine. It carves the stone. We can talk about how accurately it does what it does, we can talk about the surface quality it leaves behind. We can even talk about what geometries it can or can’t tackle due to the particular arangement of the arm and the spindle.

If those “datasheet properties” are good enough, then all you need to do is get a good artist who is handy with some modelling software let them play around with it and you will get your “awe inspiring”.