[zellyn]

I love this. It makes me believe that our sci-fi future might be more in line with the Timeless Way of Building than with cinderblock utilitarianism.

I too would love to see a 3D environment built from these, so we could get a feel for them.

[sitkack]

I'd like to apply ML to individual and group behavior in a building (biometrics, activity, location, laughter, concentration) and create a built environment that satisfies unconscious preferences for both static and dynamic uses. The best possible terrarium for humans.

[zellyn]

“The best possible terrarium for humans” — I love that. All watched over by machines of loving grace, I presume :-)

[falsedan]

'cinderblock utilitarianism' is exactly in-line with _The Timeless Way of Building_. Four square walls and a peaked roof? Job done for the next 300 years.

[zellyn]

Mea culpa. I think I was using “The Timeless Way of Building” as shorthand for “Pattern Language”. Or at least, I was thinking of the list of desirable properties rather than the method of construction.

Of course, if you designed and built such a thing all at once using a giant 3D printer, I guess you'd be building in an entirely new way, which would be completely different :-)

[mkj]

Did you miss the part about "light on two sides of every room"? These evolved designs seem optimised for nothing that actually matters to human comfort.

[zellyn]

I took this as an initial exploration of genetic algorithms for architecture. As such, the idea is more interesting than the specific parameters and weights chosen here.

You'll notice as you scroll down that this article _does_ vary the parameters and weights. For instance, the one that optimizes for windows tends to create interior courtyards.

I could imagine adding parameters and weights for thresholds, areas for crafts, light on two sides of rooms, rectilinearity, water shedding, etc. etc. etc.

But I love the idea that what comes out the other end is wildly weird and yet functional, and feels organic and nest-like rather than square.

[sitkack]

The resulting designs could be fed through a variety of simulators, environmental, social, construction feasibility, etc.

One could also use a supervised classifier and have people rank the resulting designs. They can know what they like, but not why.

[xaedes]

One could be cheap and use something like "The Sims" for evaluation and then optimize building that are possible to build there.

You would probably get more realistic buildings due to the different constraints on them.

I don't think the results should be taken to serious, but I imagine it serious fun to see them. xD

[jmilloy]

Credit to the author -- I think the optimized-for-windows results have been added since this was posted here.

[zellyn]

I posted my comment after reading the article, which included optimized-for-windows results. Of course, others may have had it sitting around in a browser tab for a while…

[jmilloy]

Yep. Unfortunately some folks are getting downvoted for reasonable criticisms that make no sense now that the post has been updated.

[sitkack]

It is a PoC, I think a lot of folks are being overly critical of the outcome and not focusing on the technique.