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

LLMs for Engineering: Teaching Models to Design High Powered Rockets

arxiv.org

Post reply on HN
Print view View original

11–20 of 46 posts

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#11

Post by neodypsis »

Workaccount2 wrote: post #2

My hypothesis is until they can really nail down image to text and text to image, such that training on diagrams and drawings can produce fruitful multi modal output, classic engineering is going to be a tough nut to crack. Software engineering lends itself greatly to LLMs because it just fits so nicely into tokenization. Whereas mechanical drawings or electronic schematics are sort of more like a visual language. Im…

Try one of the models with good vision capabilities and ask it to output code using build123d.

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#12

Post by flipflipper »

Workaccount2 wrote: post #2

My hypothesis is until they can really nail down image to text and text to image, such that training on diagrams and drawings can produce fruitful multi modal output, classic engineering is going to be a tough nut to crack. Software engineering lends itself greatly to LLMs because it just fits so nicely into tokenization. Whereas mechanical drawings or electronic schematics are sort of more like a visual language. Im…

Try having it output the circuit in SPICE. It actually works surprisingly well and does a good job picking out components values for parts and can describe the connectivity well. It falls apart when it writes the SPICE (professionally, there isn’t really one well accepted syntax really)and making the wires to connect your components, like you say missing the minds eye. But I can imagine adding a ton spice schematics with detailed descriptions with maybe an LLM optimized SPICE syntax to the training data set… it’ll be designing and simulating circuits in no time.

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#13

Post by DaiPlusPlus »

akomtu wrote: post #10

Imagine a fake engineer who read books about engineering as scifi, and thanks to his superhuman memory, he's mastered the engineer-speak so well that he sounds more engineery than top engineers in the world. Except that he has no clue about engineering and to him it's the same as literature or prose. Now he's tasked with designing a bridge. He pauses for a second and starts speaking, in his usual polished style: "sur…

> Think of the absurdity of trying to understand the Pi number by looking at its first billion digits and trying to predict the next digit. And think of what it takes to advance from memorizing digits of such numbers and predicting continuation with astrology-style logic to understanding the math behind the digits of Pi.

I'm prepared to believe that a sufficiently advanced LLM around today will have some "neural" representation of a generalization of a Taylor Series, thus allowing it to "natively predict" digits of Pi.

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#14

Post by weq »

akomtu wrote: post #10

Imagine a fake engineer who read books about engineering as scifi, and thanks to his superhuman memory, he's mastered the engineer-speak so well that he sounds more engineery than top engineers in the world. Except that he has no clue about engineering and to him it's the same as literature or prose. Now he's tasked with designing a bridge. He pauses for a second and starts speaking, in his usual polished style: "sur…

You have decribed enron musk perfectly without probably even meaning to. I concur that we have "software engineers" in every role at our tech company now that the general populous has learnt how to use chatgtp. This leads to some interesting conversations as above.

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#16

Post by discordance »

Workaccount2 wrote: post #2

My hypothesis is until they can really nail down image to text and text to image, such that training on diagrams and drawings can produce fruitful multi modal output, classic engineering is going to be a tough nut to crack. Software engineering lends itself greatly to LLMs because it just fits so nicely into tokenization. Whereas mechanical drawings or electronic schematics are sort of more like a visual language. Im…

Mechanical drawings and schematics are visualizations for humans.

If you look at the data structure of a gerber or DWG, it’s vectors and metadata. These happen to be great for LLMs.

My hypothesis is that we haven’t done the work on that yet because the market is more interested in things like Ghibli imagery.

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#17

Post by echoangle »

davemp wrote: post #7
slicktux wrote: post #3

Earlier quoted context omitted.

Electrical schematics can be represented with linear algebra and Boolean logic… Maybe their being able to “understand” such schematics is just a matter of them becoming better at mathematical logic…which is pretty objective.

Not entirely true. Routing is a very important part of electrical schematics.

Is it? Isn’t that more like PCB design? The schematic is just the abstract connection of components, right?

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#19

Post by discreteevent »

DaiPlusPlus wrote: post #13
akomtu wrote: post #10

Imagine a fake engineer who read books about engineering as scifi, and thanks to his superhuman memory, he's mastered the engineer-speak so well that he sounds more engineery than top engineers in the world. Except that he has no clue about engineering and to him it's the same as literature or prose. Now he's tasked with designing a bridge. He pauses for a second and starts speaking, in his usual polished style: "sur…

> Think of the absurdity of trying to understand the Pi number by looking at its first billion digits and trying to predict the next digit. And think of what it takes to advance from memorizing digits of such numbers and predicting continuation with astrology-style logic to understanding the math behind the digits of Pi. I'm prepared to believe that a sufficiently advanced LLM around today will have some "neural" rep…

> I'm prepared to believe that a sufficiently advanced LLM

This is the opposite of engineering/science. This is animism.

Re: LLMs for Engineering: Teaching Models to Design High Powered Rockets

#20

Post by frumiousirc »

A fundamental problem with this entire class of machine learning is that it is based on a model / simulation of reality. "RocketPy, a high-fidelity trajectory simulation library for high-power rocketry" in this case.

Nothing against this sim in particular but all such simulations that attempt to model any non-trivial system are imperfect. Nature is just too complex to model precisely and accurately. The LLM (or other DL network architecture) will only learn information that is presented to it. When trained on simulation the network can not help but infer incorrectly about messy reality.

For example, if RocketPy lacks any model of cross breezes, the network would never learn to design to counter them. Or, if it does model variable winds but does so with the wrong mean, or variance, or skew (of intensity, period, etc) the network can not properly learn and the design will not be optimal. The design will fail when it faces reality that differs from model.

Replace "rocket" with any other thing and you have AI/ML applied to science and engineering - fundamentally flawed, at least at some level of precision/accuracy.

At the least, real learning on reality is required. Once we can back-propagate through nature, then perhaps DL networks can begin to be actually trustworthy for science and engineering.

Post reply on HN