Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI for American-produced cement and concrete

engineering.fb.com

Post reply on HN
Print view View original

91–100 of 127 posts

Re: AI for American-produced cement and concrete

#91

Post by Silamoth »

cucumber3732842 wrote: post #70
alephnerd wrote: post #8

Earlier quoted context omitted.

^ This. Civil Engineering is hard, and concrete is a perfect example of how something as "simple" as concrete in reality requires significant interdisciplinary collaboration with domain experts in ChemE, MatSE, Physics, Applied Math, and CS. Some of the most robust HPC applications I saw back when I was an undergrad were done by Civil and Structural Engineers in the ONG space.

[flagged]

That’s funny because I don’t see civil engineers being “glazed” much online. Usually they’re the butt of jokes and ridicule from other engineering majors who perceive civil engineering as less ‘rigorous’ than other disciplines. I’m curious where you see this civil engineering “glazing”?

Re: AI for American-produced cement and concrete

#92

Post by ortusdux »

bluGill wrote: post #87
m4rkuskk wrote: post #46

Earlier quoted context omitted.

This may work on a small scale, not in most commercial use cases. A typical deck pour (400cy) will pour at 70-80cy/hr. you got 9-10cy/truck. Meaning you have 7 to 8 minutes to back in the truck, empty it into the hopper and leave. You barely have time to add water to the mix. Most high-volume concrete plants are "dry-batch", which means all the ingredients get dumped into the drum and the concrete will get mixed whil…

In the large road projects I've seen they bring a concrete plant to the job. Buildings still get trucks coming in.

I highly recommend the 9 episode miniseries podcast The Big Dig from GBH. Their mismanagement of the concrete was wild.

Re: AI for American-produced cement and concrete

#93

Post by cucumber3732842 »

Silamoth wrote: post #91
cucumber3732842 wrote: post #70

Earlier quoted context omitted.

[flagged]

That’s funny because I don’t see civil engineers being “glazed” much online. Usually they’re the butt of jokes and ridicule from other engineering majors who perceive civil engineering as less ‘rigorous’ than other disciplines. I’m curious where you see this civil engineering “glazing”?

They're usually held up to as the pinnacle of "real engineers" in discussions where software people are trying to portray software as insufficiently rigorous.

Yeah the other varieties of "real engineer" think of them about the same way that NPs think of MDs.

Re: AI for American-produced cement and concrete

#94

Post by GorbachevyChase »

Animats wrote: post #28

Hand-held devices for testing concrete properties would be more useful. Most concrete problems come from a bad mix - too much water, not enough cement, etc. Concrete testing usually involves cutting a core out of the poured slab and sending it to a lab. Something where you stick a probe in the mix and can reject it before pouring would help. Here are some on-site concrete testers.[1] They're heavy and a pain to use.…

It’s customary to prefix these comments with credentials, so I’ll just say that I’m a roadway engineer. Sampling at the batch plant or even at the truck is not going to give you the whole story. While the most common crime of contractors is to overwater the concrete slurry to make it flowable, other problems in workmanship can arise from failing to vibrate the concrete in its forms, leaving voids, or vibrating it too much, creating segregation of the aggregate. If the finisher overworks the concrete or tries to correct the shape when it’s green, the that can compromise strength. If the concrete is finished too early, you can get delamination. If time allows and your contractor is careful they might protect the freshly poured concrete and let it cure wet. That makes a huge difference in cracking. There is also a whole world of chemical additives that structural engineers don’t even think about in the design process.

I’m not trying to say that mix doesn’t matter, or that I’m not pleased to see that Facebook is doing something a little more noble than surveillance technology, but as with a lot of construction issues, it’s just not that simple.

Re: AI for American-produced cement and concrete

#95

Post by andrewflnr »

woah wrote: post #27
kevin_thibedeau wrote: post #9

> As a result, producers need a way to rapidly explore and validate new formulations without spending months in the lab. How do you bypass the normal process of pouring test articles and testing them months and years after cure? This is fundamentally a research activity that needs to conduct verifiable science. Not something you can guess at with an LLM.

Somebody needs to coin a new term for the scattershot zero-thought AI griping that is pervasive in online comments these days. Meatslop? Obviously it's going to be more productive for a manufacturer to do a years-long curing test on 100 likely candidates instead of 100 random mixes. They obviously already screen candidates through traditional methods, but if this AI technique improves accuracy, all the better.

co-slop. In the categorical sense, slop with all the relationships reversed.

Re: AI for American-produced cement and concrete

#96

Post by GorbachevyChase »

cucumber3732842 wrote: post #70
alephnerd wrote: post #8

Earlier quoted context omitted.

^ This. Civil Engineering is hard, and concrete is a perfect example of how something as "simple" as concrete in reality requires significant interdisciplinary collaboration with domain experts in ChemE, MatSE, Physics, Applied Math, and CS. Some of the most robust HPC applications I saw back when I was an undergrad were done by Civil and Structural Engineers in the ONG space.

[flagged]

[flagged]

Re: AI for American-produced cement and concrete

#97

Post by tempaccount420 »

jmathai wrote: post #73
georgeburdell wrote: post #65

Wrong day to release this. I had to read halfway through the release before realizing it’s legitimate.

It's legitimate? I was like wtf until I saw the date and then closed the tab.

The article says "POSTED ON MARCH 30, 2026"

Re: AI for American-produced cement and concrete

#98

Post by datsci_est_2015 »

GorbachevyChase wrote: post #94
Animats wrote: post #28

Hand-held devices for testing concrete properties would be more useful. Most concrete problems come from a bad mix - too much water, not enough cement, etc. Concrete testing usually involves cutting a core out of the poured slab and sending it to a lab. Something where you stick a probe in the mix and can reject it before pouring would help. Here are some on-site concrete testers.[1] They're heavy and a pain to use.…

It’s customary to prefix these comments with credentials, so I’ll just say that I’m a roadway engineer. Sampling at the batch plant or even at the truck is not going to give you the whole story. While the most common crime of contractors is to overwater the concrete slurry to make it flowable, other problems in workmanship can arise from failing to vibrate the concrete in its forms, leaving voids, or vibrating it too…

“it’s just not that simple” - my career in industrial data science in a nutshell. Lots of large companies come into the domains I’ve worked in with grand promises, and while sometimes they move the needle in terms of what executive leadership within the industry believes is possible, they also often poison the well for us smaller firms who provide much more leveled and concrete (heh) offerings. Curse IBM, for example.

Re: AI for American-produced cement and concrete

#99

Post by ortusdux »

coryrc wrote: post #79
richwater wrote: post #43

Earlier quoted context omitted.

Traditional trucks pick up cement from a facility and rotate it to keep it from setting. They don't mix it on the fly. Any extra is considered waste is poured out.

Where did you get the idea that rotating is "to keep it from setting" and not mixing?

https://en.wikipedia.org/wiki/Concrete_mixer#Concrete_mixing...

"Special concrete transport trucks (in-transit mixers) are made to mix concrete and transport it to the construction site. They can be charged with dry materials and water, with the mixing occurring during transport. They can also be loaded from a "central mix" plant; with this process the material has already been mixed prior to loading. The concrete mixing transport truck maintains the material's liquid state through agitation, or turning of the drum, until delivery. "

Y'all both right.

Re: AI for American-produced cement and concrete

#100

Post by anarticle »

This also feels like "we're about to build a bunch of datacenters and we cannot meaningfully verify the quality of the concrete at our sites." This enables them to monitor the variables and probably not pay if it's out of spec would be my guess.

In my concrete mixer experience that's just one part of the process, lot of other crap goes wrong, forms, vibing, water, additives. I'm not pouring foundations, so my xp is only to say there's a lot going on. Guess it's a first step?

Post reply on HN