Continue to Site

Eng-Tips is the largest engineering community on the Internet

Intelligent Work Forums for Engineering Professionals

  • Congratulations waross on being selected by the Eng-Tips community for having the most helpful posts in the forums last week. Way to Go!

Revisiting Structural Engineering as a Profession vs Trade (Reboot from 2019) 9

Status
Not open for further replies.

MJB315

Structural
Apr 13, 2011
172
thread507-459807

I'd like to reboot one of my favorite threads on this forum -- the one where Kootk explains how structural engineering is a trade and that the way that our business models work is by keeping early-stage engineers in the dark about the economics.

There's more to it, but that was one of my core takeaways. You can find the entire thread here and I'll bring in the core of the piece below for convenience.

I'd like to reboot this thread by:

[ol 1]
[li]Providing some background;[/li]
[li]Asking the $100k (USD) question, and;[/li]
[li]Asking for the contrary opinions and advice. [/li]

I'll also copy and paste a few of Kootk's points from 2019 for reference at the bottom.
[/ol]

Background

I'm a structural engineer in my late thirties practicing engineering in New York State. I have a bachelors and masters in Civil Engineering (Structures Focus), practiced at three dedicated structural firms (50 people, 3 people, 10 people) and a multidisciplinary engineering firm (150 people). I've worked on my fair share of projects and for the most part, generate successful outcomes in them. I'm a licensed PE and formerly an SE (I have the quals, but just let the license lapse).

I started questioning my own career path into engineering early on in the process. I started questioning how anyone actually chooses career paths. I mentored and shifted into education (teaching Civil Engineering and Construction Technology) to explore it more. I started a start-up devoted to understanding how professionals act and think in a local geography and use video, VR, and human networks to try to expose students to the career paths that surround them. I'm in this pot, stirring the stew.

$100,000 Question.

The best way to approach career discovery with the typical high schooler tends to start with money. Not starting salary money, but a number like $100,000/year (USD). If you ask a student if they'd like to learn more about local careers and pathways -- they don't say no, but they don't exactly sit up. If you ask them if they'd like to understand the ways they can make $100K within ten years of graduation, they do. The quality of the discussion tends to increase from there, but money (of course) is important.

There are lots of discussions about work life balance, curiosity, duty, earnings in middle and advanced ages, etc...that we could add in here. Pros understand burn out. Pros understand the common desire to shift paths and try something new, finances be darned.

Students do not however. And as an educator (and as one who has been "educated"), I'm mortified that the economics of engineering is not a cornerstone of our national curricula. I know why we "say" that we do not teach it (there is so much technical material that we have to teach) but the truth is, there is time and I don't think it's in firms (therefore our industry's) interest to do so.

I think we collectively feel (fear?) that if understand the economics, they'll shift. I say, if we don't tell them and they find out later - they'll shift anyway... at a great opportunity cost to nearly everyone involved.

Going back to, "Can a Structural Engineer earn a $100,000/year within ten years of high school?" I feel like the answer is no. Fifteen-twenty years, probably.

Construction Project Management? Yes. Many other skilled trades, possibly. But engineering, no.

Push Back

Is there anything about that understanding that is inaccurate? If you're in a class full of high schoolers or college students, what do you say? What should you say?

I'm literally asking. Because as I make more career discovery content - I feel like the heavy equipment operator pathway is getting more love than the PE/SE with Two Degrees Pathway. At least to an 18 year old.

As a thirty-eight year old, I like having the club in my bag. Because I know that clients aren't just paying for product - they're paying to have someone take uncertainty away and they like doing so by someone they know and like. I also know it becomes a different way to make a $100K, which may be more appealing as we age.

But again, I'm focused on the question of what should we say to students?


--
Here's a few excerpts from the 2019 thread which I think resonate. The thread overall is great of course, here's two of Kootk's points.




Kootk said:
START KOOTK's DEFINITION OF A PROFESSION

As humans toil away, I propose that they get paid for two things:

1) The effort/labor that they put into producing their product, on a product by product basis.

2) The requisite knowledge that a practitioner must posses in order to successfully product their product.

A profession is work where compensation is dominated by knowledge rather than effort.

A trade is work where compensation is dominated by effort rather than knowledge.

Some applications of this definition.

3) Landscapers (my son last summer). 5% knowledge; 95% effort. Trade (or unskilled trade I suppose). Bodies functioning as machines.

4) The Plumber that fixes my dishwasher. 30% knowledge; 70% effort. Trade (skilled).

5) Surgeon that replaces my pacemaker. 95% knowledge; 5% effort. Profession.

6) Structural engineer?? I would say 30% knowledge; 70% effort. Trade (skilled).

But wait? Didn't I go to school for six years to get my masters? Didn't I take a dozen arcane licensing exams to prove my worth? Yeah, you did. But remember that we're not talking about what you had to do to be able to legally practice structural engineering. Instead, we're talking about what your actually getting paid for when your client contracts for your services. I submit that we're mostly getting paid for effort. In a way, structural engineering is a particularly cruel form of a trade. Imagine if plumbers had to endure six years of post secondary and endless post graduation exams and professional development?

END DEFINITION

And...

Kootk said:
Yes, issues with schedules, fees, and quality are the day to day nuisances. But, then, why do these things bother me really? All that just falls under the umbrella of "work", right? For me, these things are bothersome because they put me at odds with my own integrity almost constantly. Since we're talking big threes:

1) If an alien landed on earth and read all of our codes and design guides, they would have one impression of what structural engineers should be doing in regard to detail and rigor in design. Then, if they observed what practicing structural engineers actually do, they'd be horribly disappointing and confused. We take shortcuts. And lots of them. In fact, this is one of the first difficult lessons that new structural engineers must learn in a hurry. For me, this discrepancy between what I feel that I should be doing and what I'm actually doing is a challenge to my integrity. I tell the world that I'm delivering one product in terms of rigor and safety and then I turn around and deliver something quite different. I'm lying to the world in this respect.

2) As pointed out above, we have to commit to very aggressive schedule in order to keep winning work. This inevitably leads to agreeing to unrealistic schedules that give little account to reasonable contingencies. Yet I agree to these schedules because I feel that I have to to survive. This is me knowingly committing to delivering something that I know that I often wont be able to deliver. This is me lying to my clients and fellow project participants.

3) It is the low paid efforts of junior engineers that make our business model go 'round. Since most structural engineers get into the game to satisfy their inner nerd, the only way to keep such engineers motivated is to perpetuate their misunderstanding that society places a high value on the activity that is structural design. As a senior structural engineer, I'm guilty of this on a near constant basis. You can't very well motivate a junior by telling them "the only way to make any money at this is to get out of design and into management or sales as fast as you can". Again, this is me lying... now to junior engineers.

As structural engineers, we like to facetiously toss around the concept that we lose sleep over our work. You know, stuff falling down and crushing baby carriages etc. The truth is that none of that costs me any sleep. What does cost me sleep is my being constantly at odds with my own integrity as I've described. I think that a practicing structural engineer would actually be well served by some degree of sociopath in this respect. And, indeed, I know of some mild sociopaths that are wildly successful in structural engineering and make it look easy.


 
Replies continue below

Recommended for you

Kootk said:
Either way, I choose to celebrate survival above all else. Egos and shame are useless luxuries best left to those who get their calories from a zookeeper.

This made me laugh and hold a mental-fist-of-solidarity up in the air.
 
MJB - yes, in Aerospace it is possible to have a one person business, though it is quite rare. I left a big company after 18 years, and did consulting on my own for 13 years. I’m back at it part time after spending another 10 years at a big company. BUT, one has to develop your reputation, knowledge and skills first. And its not easy.
 
MJB said:
If you're in a class full of high schoolers or college students, what do you say? What should you say?

Thus far, we've been mostly focused on the merits of the structural engineering profession as it is now. When I consider the future of the profession, I drift back into surgeon general's warning territory.

Having learned a bit about how ChatGPT does its voodoo, I now view that kind of artificial intelligence as a threat to our profession that is existentially different from anything that came before it.

In the past, I was confident that the world would always need structural engineers because I could not see a linear path to artificial intelligence being able to do the work meaningfully in all it's complexity. Now, I do see that path.

In 20 yrs time, I suspect that society will require 80% fewer structural engineers. Just the relationship guys and a few technical guys who check and tweak. Odd as this may sound, I can even imagine the relationship guys becoming obsolete. I think that's possible when your service has "necessary evil" status. Thankfully, this won't affect me because I nailed the timing on this. For new grads, I see this as a short term supply and demand apocalypse that will require supply side resolution.

This subject, of course, probably deserves a thread of its own at some point.

I get it. At any point in time, and in any space, there's always some nutball waving his arms and predicting that the end is near. Human beings are biological storytelling machines and there's something endemic to human nature that makes us want to be present for the end of the story. It's a form of narcissism really. That said, over a long enough time horizon, one nutball will wind up being right. Is that nutball me? I hope not.
 
MJB315 said:
But I agree that $100K for aerospace engineers and CS majors within ten years of high school isn't uncommon.

I can't speak to aerospace; don't know much about it. I do know an electrical engineer who worked for chips and circuits in defense right out of college and made a shitload of money, starting in the 80k range and probably broke 100k in a few years. The defense industry is a nice tap of money for people who can get into it. (He also mentioned how he was desperately trying to get out of it because the work conditions sucked. I don't know more specifically what was bad about it, and lost contact.)

Regarding CS, I don't remember exactly where I read it, but there was an article that only a small percentage of people ended up getting high paying jobs. A vast majority of people in that field don't make the cut and give up early or end up getting low paying jobs. So I think it's lucrative for only the cream of the crop. CS isn't a magic bullet; it's really hard. I'm not saying this is definitively true, but it needs looking into and affects what should be said to students. Anecdotally, my brother does system administration and makes like $170k working for a company. But he's the kind of person that keeps up with the latest technologies and products on his own time. I don't think people would break out of the 100k barrier unless they go above and beyond what is expected, which is true in most professions, not just CS.


KootK said:
Having learned a bit about how ChatGPT does its voodoo, I now view that kind of artificial intelligence as a threat to our profession that is existentially different from anything that came before it.

I see AI in engineering more akin to when computer structural analysis and CAD became widespread. It vastly increased the productivity and expectations of engineers. The ones who didn't adapt were left behind, but it didn't invalidate the profession. So when AI becomes integrated into structural engineering, the people who can harness it will rise to the top. I can also see code officials adapting it at some point as a countermeasure, probably much later.

I wonder who will be the first to harness AI. I'm thinking it might be one of the industry giants, like Autodesk, CSI, or Bentley. People who jump on that bandwagon will be propelled into the future. At the same time, maybe this is hubris, but I strongly believe that engineers will always be needed and we won't have an 80% reduction. I just don't see an AI robot going into a crawl space, testing the water and termite damage of joists, and recommending a good solution.
 
milkshakelake said:
I just don't see an AI robot going into a crawl space, testing the water and termite damage of joists, and recommending a good solution.

Come on now, I was speaking to new build work performed in an office setting. AI won't be able to compete with the crawl space jockeys until it gets properly integrated with drone fleets.
 
Oh yeah, office design work will definitely be replaced by AI. I’m imagining something that can take an architectural BIM model (also made by AI) and design the whole building with a few text based user inputs or markups, or none at all.
 
milkshakelake said:
So when AI becomes integrated into structural engineering, the people who can harness it will rise to the top.

Agreed - but going back to the 2019-Kootk-Analysis of Trade vs. Profession - will AI make structural engineer more profession-like or more skilled-trade like?

I do think AI is coming for new construction structural design - how could it not? When consulting on new work, I used to think of myself less like an engineer and more like a tailor. The main challenge was pushing and pulling components around to fit the geometry of the building. A lintel here, a kicker there. A braced frame here, a column transfer there.

As soon as the geometry of the structure was set...well, a lot of the human-heavy work was done. I'd hot potato the geometry into an analysis program and viola, member sizes. Then of course, there was some baton passing back and forth during the smoothing, checking and document preparation parts of the design work...until humans were back in the saddle for the permitting/bidding/construction administration of a job. That workflow actually suited me, personally -- enjoying the human part of the profession more than the plugging/chugging.

Can AI take over that tailoring and document preparation part of that workflow? Yeah. Is it possible (and likely) that Autodesk is feeding a self-learning AI all of humanity's design codes, a sample set of past designs, and cutting it loose in a self-learning, millions-of-human-years-in-a-day, guess-and-check system -- with the solution being a structural system that meets code and fits within an architectural model? Yeah, how could it not?

Does it mean that humans are 100% out of the loop? No. I do think humans will be in the driver seat for any forensic, restoration, and other "Carhartt" wearing roles. Is that about 20% of today's current market? Feels like it could be.

What happens to the other 80%? They probably get priced out, right? How can future developers and public clients want to pay what is already pitiful percentage of a construction cost when 2030-era AI is churns out code-compliant-and-well-tailored structural designs for moderately complex buildings in a blink?

I think Kootk is right to get the "Surgeon General's warning label" out there now and spark a real discussion within our schools and firms.

What that discussion is and what it should be, honestly, is the thing I'm noodling on. This thread is a useful sounding board. I really do want to root for the civil-structural-hometeam, while at the same time as I am cleared eyed about how my future students will earn a living.
 
Well, like any human navigating a complex topic. I decided to bounce it off of OpenAI's ChatGPT for assistance. This AI conversation took about 60 seconds to complete.

[MJB315]
Do you think that AI will be capable of replacing many professional building structural engineers? If so, why? If not, why not?

[AI-ChatGPT]
As an AI language model, I can say that AI has the potential to revolutionize the field of structural engineering and make the work of human structural engineers more efficient and accurate. However, it is unlikely that AI will fully replace professional building structural engineers in the foreseeable future.

There are several reasons for this. Firstly, while AI can perform complex calculations and analyze data, it does not have the same level of creativity, intuition, and problem-solving skills that human engineers possess. These skills are often critical in designing structures that are both safe and functional while also meeting aesthetic and practical considerations.

Secondly, building structures are not static; they are subject to changes over time due to factors such as weather, natural disasters, and wear and tear. Human engineers are better equipped to anticipate and respond to these changes, and they have the experience to apply judgment and adjust designs as needed.

Thirdly, there are ethical and legal considerations involved in the field of structural engineering. Engineers have a responsibility to ensure that their designs are safe and comply with applicable regulations and standards. AI, while capable of analyzing data, cannot be held accountable for its decisions in the same way that human engineers can be.

In summary, while AI has the potential to enhance the work of structural engineers, it is unlikely that it will fully replace them in the foreseeable future. Human engineers possess skills, experience, and judgment that are critical to the field, and they are better equipped to respond to the dynamic and complex nature of building structures.


[MJB315]
I agree in general, but I disagree when it comes to the design of new building structural systems. For example, do you think that an AI system could layout the structural steel frame of a four story building, if it was given many examples to mimic?

[AI-ChatGPT]
Yes, an AI system could potentially layout the structural steel frame of a four-story building, given sufficient examples to learn from. AI systems are capable of analyzing large amounts of data and identifying patterns, which could be applied to designing a building's structural system.

However, it is important to note that while AI can automate some aspects of the design process, it cannot replace the expertise and experience of human structural engineers. Structural engineering is a complex field that involves many factors beyond just the structural layout, including factors such as site conditions, building codes and regulations, and the building's intended use. A human engineer would still need to review and approve the AI-generated design, and make adjustments as needed to ensure it meets safety, regulatory, and practical requirements.

Furthermore, while AI can be trained to design buildings based on previous examples, it may not be able to account for unique or unusual design challenges that require creative problem-solving skills. Human engineers possess the judgment and intuition to make decisions in complex situations that an AI system may not be able to replicate.

In summary, while AI can assist in some aspects of the design process, human engineers will likely remain an essential part of the structural engineering field for the foreseeable future.

[MJB315]
I agree with your assessment. Based upon the amount of time it takes to design a building now, do you believe that the amount of human effort would be reduced by an order of magnitude?

[AI-ChatGPT]
It is possible that AI could reduce the amount of human effort required in the design of buildings, but it's difficult to predict an exact order of magnitude.

AI could potentially automate many of the time-consuming tasks involved in the design process, such as creating initial design options, optimizing the design for cost and performance, and generating detailed engineering drawings. This could free up human engineers to focus on more complex and creative tasks that require their expertise and experience.

However, it's important to note that the complexity of building design means that human engineers will likely still be involved in the process to some degree. While AI can assist with certain tasks, it may not be able to account for all the nuances and complexities involved in building design, especially when dealing with unique or unusual design challenges.

Furthermore, the adoption and integration of AI into the design process may require significant investment in technology and training, which could offset some of the potential time savings.

In summary, while AI could potentially reduce the amount of human effort required in building design, it's difficult to predict an exact order of magnitude. The extent to which AI can be integrated into the design process will depend on many factors, including the complexity of the design, the level of investment in technology and training, and the evolving capabilities of AI systems.

[MJB315]
Thanks!

[AI-ChatGPT]
You're welcome! If you have any more questions or if there's anything else I can help you with, feel free to ask.

[MJB315]
Actually, I have two more questions!

[AI-ChatGPT]
Sure, I'm happy to help. What are your questions?

[MJB315]
First, do you think that AI will increase the average salary of a professional structural engineer in future years or decrease it?

[AI-ChatGPT]
It's difficult to predict the impact of AI on the salaries of professional structural engineers.

On one hand, AI has the potential to increase the efficiency and productivity of engineers, which could lead to increased demand for their services and potentially higher salaries. AI could also enable engineers to take on more complex and challenging projects, which could also lead to higher salaries.

On the other hand, AI could also automate certain aspects of the engineering process, which could potentially reduce the number of engineers required for a given project. This could lead to increased competition for engineering jobs and potentially lower salaries.

Ultimately, the impact of AI on engineering salaries will depend on many factors, including the pace of AI adoption, the evolving capabilities of AI systems, and the overall demand for engineering services. It's difficult to predict with certainty what the future holds, but it's likely that AI will continue to play an increasingly important role in the engineering profession in the years ahead.

It's worth noting, however, that the value of a professional engineer goes beyond their technical skills and includes their judgment, creativity, and ability to manage projects and work collaboratively with other professionals. These are skills that are not easily replaced by AI and could help ensure the continued demand for professional engineers and their salaries.

[MJB315]
Understood. My second question is do you believe that structural engineering is more like a "profession" or more like a "skilled trade?"

[AI-ChatGPT]
Structural engineering is typically considered a "profession" rather than a "skilled trade."

A profession is generally defined as a type of work that requires specialized knowledge, education, and skills, and is governed by ethical standards and codes of conduct. Professionals are expected to exercise judgment and discretion in their work and to act in the best interests of their clients or the public.

Structural engineering certainly fits this definition. Structural engineers typically have advanced degrees in engineering or a related field, and are required to be licensed in order to practice. They are responsible for ensuring the safety and stability of buildings and other structures, and are expected to adhere to professional standards and codes of ethics.

While there are certainly some aspects of structural engineering that could be considered a "skilled trade" (such as the physical construction and installation of structural elements), the overall nature of the work and the level of expertise required typically place it within the realm of a "profession."

[MJB315]
Ok, thanks!

[AI-ChatGPT]
You're welcome! If you have any more questions, feel free to ask.
 
Assuming that this was not "appropriate to the first of April", how do I give ChatGPT a purple star?

[sub][ ]—————————————————————————————————[/sub]
[sup]Engineering mathematician/analyst.[ ] See my profile for more details.[/sup]

 
MJB315 said:
I decided to bounce it off of OpenAI's ChatGPT for assistance.

While that was entertaing -- and I've no doubt that's all that you intended the exercise to be -- I feel it important to add some context to ChatGPT's statements.

ChatGPT does not know -- or think -- anything at all. It's just a pattern recognizing mimicry device on the grandest of scales. So its responses are really just a statistical averaging of how humans would currently answer your questions. And humans most definitely have a horse in this particular race.

There's significant irony in this I feel:

1) ChatGPT is a threat precisely because it can do impressive things without really "knowing" anything at all.

2) One of the many things that ChatGPT does not "know" is the true nature of the threat that ChatGPT poses.

ChatGPT is like a virus in this regard. Chat GPT has no malicious intent. In fact, it ChatGPT has no intent at all. But it's still going to tear through its host come hell or high water.

For what it's worth, it's not been my intent to disparage viruses or ChatGPT. I have great admiration for both.
 
If a profession is where you are paid for knowledge, rather than effort.

We must realize the more rare your knowledge is, the more its worth. the more common your knowledge is, the less its worth. if you have nothing special to offer knowledge wise, you're going to need to break a sweat to earn a buck.

Beats me why, at all the offices i've ever worked at, the specialized teams really struggled to recruit staff, while the generic structural and civil teams always had abundant staff and plenty of fresh blood. Over at the special teams we got paid more, did more interesting work, worked less hours, and were allotted more time for research for our projects. the regular structural guys were always stressed to the max trying to pump out building designs in unrealistic timelines. putting out fires left and right.

Engineers designing the same old steel beam and timber stud over and over again, like every other engineer in town, will be forced into competition, and there will be a race to the bottom.

Engineers keen to specialize, learn things that not many other engineers know, work in odd and unique areas, will become paid for their rare knowledge.

I started my own company in the specialized world a few years ago, and definitely dont have the money complaints a lot of engineers here gripe about. i dont need to advertise. to be honest, i dont really try that hard. the work is abundant, lucrative, and i can pick and choose it.
 
While I can see AI stream lining some things....I just have a hard time picturing it having a tremendous impact on the profession considering I haven't worked with a human designer (in the last 15 years) who could give me a decent layout....and I see errors by live structural engineers every day.

So while I can see it making a impact on the design of your average commercial building (that's a lost cause to me anyway; you can't make money at it).....a modification for (say) a existing industrial building? Can't see it.
 
Google Bard's view:

Bard said:
I believe that structural engineering is more like a profession than a skilled trade. Structural engineers use their knowledge of mathematics, physics, and materials science to design and analyze structures that are safe, efficient, and aesthetically pleasing. They must also be able to communicate their designs to other members of the construction team, including architects, contractors, and fabricators. This requires a high level of education, training, and experience.

Skilled trades, on the other hand, typically involve the use of hands-on skills to create or repair products or structures. Structural engineering, on the other hand, is a more cerebral profession that requires a strong understanding of engineering principles.

Of course, there is some overlap between structural engineering and skilled trades. For example, structural engineers may need to work with skilled tradespeople to fabricate and install their designs. However, I believe that the level of education, training, and experience required for structural engineering makes it more of a profession than a skilled trade.

ChatGPT is a bit ahead I think!

It all hinges on what you define as 'effort'.
 
KootK said:
In 20 yrs time, I suspect that society will require 80% fewer structural engineers.

MSL said:
but I strongly believe that engineers will always be needed and we won't have an 80% reduction. I just don't see an AI robot going into a crawl space, testing the water and termite damage of joists, and recommending a good solution

I'm 100% with KootK on this one, and I'd take it further. The profession varies quite a bit so there will be exceptions, but I think 20 years is being too generous for us apes.

For new building design large firms have been playing seriously with AI for a few years now. I assume that this is going to accelerate and that most large firms will be regularly using AI in some fashion this year. It will trickle down to medium and small firms, or the medium and small will get squashed out of existence. There will not be a binary shift where one day a robot is sitting at a desk doing slab design. The tasks that AI handles will grow in complexity and as a percentage of the overall work. It'll be a while before it does everything soup to nuts but that's not necessary. We will become like pilots overseeing autopilot - maybe takeoff and landing needs us to keep an eye on it (maybe) but that's about it.

Crawlspaces and renovations are not immune. A robot isn't going to crawl under a house. But instead of getting Bill the local engineer you'll have Todd, the 23 year old technician carrying some AI tools around of increasing complexity over time. Other than mobility what is beyond imagining the AI doing? At first it'll make mistakes and people will mock it, "that's why you need old Bill, he's been doing this for 30 years" but over time the AI will get better. Eventually the tech will serve as little more than legs to move the AI around as it commands. Imagine it like having the job of wheeling stephen hawkings around, sure you're needed but you're certainly not in a great bargaining position.

The natural language answers such as those posted above are neat but can be sort of chalked up to a parlor trick. Try using chatgpt to perform actual engineering tasks and you see where this is headed. I've just recently started messing with it and I'm convinced.
 
Kootk said:
ChatGPT does not know -- or think -- anything at all. It's just a pattern recognizing mimicry device on the grandest of scales.

I know -- and that's what spooks me too. Humans tend to be walking-talking mimicry-machines, and now we're fascinated by an even grander mimicry-machine... but the grander micmiry-machine is just mimicing us back to ourselves, so we can consult and mimic it, and (insert doom-loop-to-the-abyss discussion here).

If you follow this logic long enough, I keep coming back to the need to develop a human system that collects and safeguards human-generated expertise for a later date. It won't be long where young generations will not able to discern one from of expertise another, and if the artificial expertise machines go astray or become malevolent - we won't be in a position to reboot our human expertise system without feedstock from earlier times.

Honestly, I often think that the human-generated ways of executing tasks (certain in the construction, civil/structural industry) was more effective at times at generating positive results. Maybe not as efficient - but effective.

If capturing and safeguarding human expertise is valuable, I feel like time is short. Most of the "mostly-human-generated expertise" lives in the heads of the Baby Boomer generation - but that generation is statistically half-out of the workforce as of now and will be nearly entirely out in a blink. The time to capture and safeguard is now, if we're going to do it.

The university system used to be our institution tasked with both generating new and safeguarding old human expertise for future retrieval. But I'm not sure it's functioning that way anymore. Insert discussion on the university systems here.

But other than higher education, I'm not aware of any system that is capturing and safeguarding human expertise. If they are out there, what are they?

 
+ the one possible bright spot. Perhaps this will offer a new playing field for everyone. If I'm able to effectively leverage AI along with my software to do the work of 10 engineers, can I now compete with a firm that was carrying a big staff, office space, etc etc and has to offload all of that? This may offer an opportunity in the short term for some interesting re-alignments.
 
bookowski,

It's my understanding that these llm AIs are running off of hundreds of High End GPU cards simultaneously. Are you renting your AIs or are you wealthy enough to build a warehouse to store the servers that your AIs will run on? Tongue slightly in cheek, but there is (currently) a very high cost to operating an AI.

As for the future of our professional trade, I think from the legal perspective, there will always be a requirement that there is an actual human that is taking responsibility for the designs. Maybe this will change in 10-80 years, but in the meantime there will be a definite "who's going to take the time to develop a young engineer to take over the business when you can hire an AI army to design everything" problem.

Please note that is a "v" (as in Violin) not a "y".
 
This discussion makes me think of the movie Idiocracy, with the old skyscrapers strapped together and leaning on the last structurally sound one, doctors replaced with AI, and lawyers getting their degrees from Costco.
 
I'd be renting it, everyone would. The same way almost everyone rents all kind of stuff now. I don't see that being a barrier.

Yes, maybe an actual human needs to be held responsible - but that doesn't sound like much hope. Any time the argument devolves into "there needs to be a guy" I think that proves the point. Sure, just like the autopilot there is a guy - lots of them. But there is nowhere near what we have now, not even close.
 
I feel that those here who view AI's eventual encroachment upon our work as an opportunity are making an important error. That error, in my opinion, is in assuming that it will be structural engineers who wield the AI's. Like one might have invested in a cotton gin in 1805 in order to give one's factory a temporary marketplace advantage and crush the factory down the street.

I don't believe that it will be structural engineers wielding the AI's. I don't even think that it will be our software vendors like Bentley and RISA that will "own the means of production". I suspect that it will be building developers that wield the AI's, most likely via rental agreements. And this will eliminate the need for owners to have any kind of meaningful, up front end relationships with their human design consultants whatsoever.

I see the new build, EOR design process of the future being something like this:

1) Developer asks ChatGPT for five, fully priced options for an eight story condo tower on a site in Pheonix. No architects, no engineers so far. No relationships that would justify the existence of some design team "relationship guys".

2) Without even knowing what a building is, ChatGPT will access its worldwide library of BIM models and PDF drawings to generate the five options via pattern recognition. These will probably be permit level ASME drawings. This exercise will be, effectively, instantaneous and free compared to the way that things are done now.

3) The developer will have ChatGPT tweak the design a bit. "Put the stair shaft on the north end instead". "Add in some ADA parking spots over here". "Put the entry canopy of option #2 on option #5".

4) The developer will take their permit drawings over to Upwork.com and ask the hungry engineers and architects there to bid on the opportunity to review, tweak, and stamp ChatGPT's permit drawings.

This is the dystopian hell that concerns me . Sure, there will be a few "spaces" for structural engineers to hide. Good luck selling any of that to college kids who dream of participating in major, new build architecture and infrastructure works.

The reason that firms have traditionally struggled to staff "special projects" teams is because, from the perspective of your typical new grad, "special projects" is usually a euphemism for crap work that most deem undesirable: forensics, construction engineering, delegated design, unglamorous renovations... These spaces do pay wall and do provide improved quality of life. I don't feel that is because they require rarified knowledge however. It's primarily because the "crap work" perception creates a favorable labor supply situation. It may not be so favorable once there's nothing else for us to do.

C01_qmn3xj.png
 
Status
Not open for further replies.

Part and Inventory Search

Sponsor