[HN Gopher] LLMs for Engineering: Teaching Models to Design High...
       ___________________________________________________________________
        
       LLMs for Engineering: Teaching Models to Design High Powered
       Rockets
        
       Author : tamassimond
       Score  : 119 points
       Date   : 2025-04-30 22:03 UTC (2 days ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | Workaccount2 wrote:
       | 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.
       | Image art but with very exacting and important pixel placement,
       | with precise underlying logical structure.
       | 
       | In my experience so far, only O3 can kind of understand an
       | electronic schematic, but really only at a "Hello World!" level
       | difficulty. I don't know how easy it will be to get to the point
       | where it can render a proper schematic or edit one it is given to
       | meet some specified electronic characteristics.
       | 
       | There are programming languages that are used to define drawings,
       | but the training data would be orders of magnitude less than what
       | is written for humans to learn from.
        
         | slicktux wrote:
         | 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.
        
           | davemp wrote:
           | Not entirely true. Routing is a very important part of
           | electrical schematics.
        
             | echoangle wrote:
             | Is it? Isn't that more like PCB design? The schematic is
             | just the abstract connection of components, right?
        
               | davemp wrote:
               | I would consider a PCB schematic to be part of an
               | electrical schematic. Even if you don't, you still have
               | to consider final layout because some lines will need EMF
               | protection. The linear equations and boolean algebra are
               | just a (extremely useful) model after all.
        
           | nyrikki wrote:
           | This paper works because it _explicitly_ is a problem domain
           | that was intentionally constrained to ensure safety in the
           | Amateur high-power rocket hobby. Specifically with
           | constraints and standards that were developed for teenagers
           | of various skill to do with paper and pen well before they
           | had access to containers. While modern applications have
           | added more functions, those core constrains remain.
           | 
           | It works explicitly because it doesn't hit the often counter-
           | intuitive limitations with generalization in pure math.
           | 
           | Remember that Boolean circuit satisfiability is NP-complete,
           | and is beyond UHAT's + poly length CoT expressibility, which
           | is capped at PTIME.
           | 
           | Even int logic with boolean circuits is in PSPACE.
           | 
           | When you start to deal with values, you are going to have to
           | add in heuristics and/or find reductions that will cost your
           | generalizability.
           | 
           | Even if you model analog circuits as finite labelled directed
           | graphs with labelled vertices, similar to what Shannon used;
           | removing some of the real world electrical impacts and focus
           | on them as computational units, the complexity can get crazy
           | fast.
           | 
           | Those circuits, with specific constraints (IIRC local
           | feedback, etc..) can be simulated by a Turing machine, but
           | require ELEMENTARY space or time, and despite it's name
           | ELEMENTARY is iterated exponential: 2^2^2^2^2^...^n with k
           | n's.
           | 
           | Also note that P/poly, viewed as problems that can be solved
           | by small circuits is not a _practical_ class and in fact
           | contains all of the unary languages that we know are
           | _unsolvable_ by real computers in the general case.
           | 
           | That apparent paradox that P/poly, which has small bool
           | circuits, also contains all of those undecidable unary
           | languages is a good starter into that rat hole.
           | 
           | While we will have tools and models that are better at math
           | logic, the constrains are actually limits on computation in
           | the general case. Generalization often has these types of
           | costs, and the RL benefits in this case relate to
           | demonstrating that IMHO.
        
         | heisenzombie wrote:
         | My experience is that SOTA LLMs still struggle to read even the
         | metadata from a mechanical drawing. They're getting better --
         | they now are mostly ok at reading things like a BOM or revision
         | table -- but moderately complicated title blocks often trip
         | them up.
         | 
         | As for the drawings themselves, I have found them pretty
         | unreliable at reading even quite simple things (i.e. what's the
         | ID of the thru hole?), even when they're specifically
         | dimensioned. As soon as spatial reasoning is required (i.e.
         | there's a dimension from A to B and from A to C and one asks
         | for the dimension B to C), they basically never get it right.
         | 
         | This is a place where there's a LOT of room for improvement.
        
           | Terr_ wrote:
           | I'm scared of something like the Xerox number-corruption bug
           | [0], where some models will subtly fuck everything up in a
           | way that is too expensive to recover from by the time it's
           | discovered.
           | 
           | [0] https://www.dkriesel.com/en/blog/2013/0802_xerox-
           | workcentres...
        
         | tintor wrote:
         | Problem #1 with text-to-image models is that focus is on
         | producing visually attractive photo-realistic artistic images,
         | which is completely orthogonal from what is needed for
         | engineering: accurate, complete, self-consistent, and error-
         | free diagrams.
         | 
         | Problem #2 is low control over outputs of text-to-image models.
         | Models don't follow prompts well.
        
         | yieldcrv wrote:
         | Tell it how to read schematics in the prompt
        
         | neodypsis wrote:
         | Try one of the models with good vision capabilities and ask it
         | to output code using build123d.
        
         | flipflipper wrote:
         | 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.
        
           | kurthr wrote:
           | Yeah, how to you thing that schematic is represented
           | internally? How do you think the netlist is modeled? It's
           | SPICE and HDL all the way down!
           | 
           | There are good reasons not to vibecode Verilog, but a lot of
           | test cases are already being written by LLMs and the big EDA
           | vendors (Cadence, Synopsys, Siemens) all tout their new AI
           | capabilities.
           | 
           | It's like saying it can't read handwritten mathematical
           | formulas, when it solves most math problems in markup (and if
           | you aren't using it you're asking for trouble).
        
           | flipflipper wrote:
           | I brainfarted a bit and mixed up my attempts with making
           | LTSPICE asc schematics (which are the text representations of
           | the GUI sch, with wires) with the normal node based SPICE
           | syntax. I just tried this specifically asking for spice to
           | run with ngspice to run in a CLI. Seemed to run great! Going
           | to play around with this for a bit now...
        
         | discordance wrote:
         | 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.
        
           | danielbln wrote:
           | Ate you being facetious or is that really your hypothesis?
        
             | notahacker wrote:
             | Not the OP, but Ghibli imaging doesn't kill people or make
             | things stop working if it falls into uncanny valley
             | territory, so the bar for a useful product is lower than a
             | "designer" based on a NN which has ingested annotated CAD
             | files...
        
           | jayd16 wrote:
           | More like there isn't a resource of trillions of user
           | generated _schematics_ uploaded to the big tech firms that
           | they can train on for free by skirting fair use laws.
        
         | imranq wrote:
         | You can describe a diagram with markdown like mermaid, so you
         | can at least understand state changes and processes which are
         | core to engineering.
        
         | rjsw wrote:
         | Programming languages don't really define drawings. There are
         | several standards for the data models behind the exchange file
         | formats used in engineering though.
         | 
         | Someone could try training a LLM on a combination of a STEP
         | AP242 [1] data model and sample exchange files, or do the same
         | for the Building Information Model [2].
         | 
         | [1] http://www.ap242.org/ [2]
         | https://en.wikipedia.org/wiki/Industry_Foundation_Classes
        
       | aaron695 wrote:
       | I think what might work is people coming together around this LLM
       | like a God.
       | 
       | Similar to Rod of Iron Ministries (The Church of the AR-15)
       | Taking what is says, fine tuning it, testing it, feeding back in
       | and mostly waiting as LLMs improve.
       | 
       | LLMs will never be smarter than humans, but they can be a meeting
       | place where people congregate to work on goals and worship.
       | 
       | Like QAnon, that's where the collective IQ and power comes from,
       | something to believe in. At the micro level this is also mostly
       | how LLMs are used in practical ways.
       | 
       | If you look to the Middle East there is a lot of work on rockets
       | but a limited community working together.
        
         | otabdeveloper4 wrote:
         | Okay. As long as they don't start sacrificing virgins to the
         | Prompt Gods.
        
       | akomtu wrote:
       | 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: "sure, let me
       | design a bridge for you." And while he's talking, he's starring
       | at you with his perfect blank face expression, for his mind is
       | blank as well.
       | 
       | 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.
        
         | DaiPlusPlus wrote:
         | > 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.
        
           | discreteevent wrote:
           | > I'm prepared to believe that a sufficiently advanced LLM
           | 
           | This is the opposite of engineering/science. This is animism.
        
             | otabdeveloper4 wrote:
             | I want to believe, man. Just two more layers and this thing
             | finally becomes a real boy.
        
           | walleeee wrote:
           | Anthropic had a recent paper on why llms can't even get e.g.
           | simple arithmetic consistently correct, much less generalize
           | the concept of infinite series. The finding was that they
           | don't find a way to represent the mechanics of an operation,
           | they build chains of heuristics that sometimes happen to
           | work.
        
           | kneegerman wrote:
           | Sometimes I feel this website, very much like LLMs
           | themselves, prove that handling of language in general and
           | purple prose in particular have absolutely no (as in 0)
           | correlation with intelligence.
        
             | DaiPlusPlus wrote:
             | I suspect your definition of "intelligence" differs from
             | mine.
        
         | weq wrote:
         | 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.
        
         | buescher wrote:
         | It's worse than that. Imagine he's consistently plausibly wrong
         | about everything, but when you point that out, people think
         | it's just sour grapes at how smart he is.
        
           | imtringued wrote:
           | That's not even the worst part. The worst part is that there
           | are people who fit this description as well, and the
           | singularity crowd anthropomorphizes the "human" flaws of the
           | AI as proof of human level intelligence.
        
       | revskill wrote:
       | How about halting problem ? I see llm often got infinite
       | recursive problem.
        
       | simianwords wrote:
       | More evidence that we need fine tuned domain specific models.
       | Some one should come up with a medical LLM fine tuned on a 640b
       | model. What better RL dataset can you have than a patient with
       | symptoms and the correct diagnosis?
        
       | frumiousirc wrote:
       | 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.
        
         | londons_explore wrote:
         | > all such simulations that attempt to model any non-trivial
         | system are imperfect.
         | 
         | I believe the future of such simulation is to start from the
         | lowest level - ie. schrodinger's equation, and get the
         | simulator to derive all higher level stuff.
         | 
         | Obviously the higher level models are imperfect, but then it's
         | the AI's job to decide if a pile of soil needs to be simulated
         | as a load of grains of sand, or as crystals of quartz, or as
         | atoms of silicon, or as quarks...
         | 
         | The AI can always check its answer by redoing a lower level
         | simulation of a tiny part of the result, and check it is
         | consistent with a higher level/cheaper simulation.
        
           | xigency wrote:
           | > I believe the future of such simulation is to start from
           | the lowest level - ie. schrodinger's equation, and get the
           | simulator to derive all higher level stuff.
           | 
           | I do hate to burst your bubble here but I've been doing real-
           | time simulation (in the form of games, 2D, 3D, VR) for enough
           | decades to know this is only a pipe-dream.
           | 
           | Maybe at the point when we have a Dyson sphere and have all
           | universally agreed upon the principles that cause an airfoil
           | to generate lift this would be possible, otherwise it's
           | orders of magnitude beyond all of the terrestrial compute
           | that we have now.
           | 
           | To quote Han Solo, the way we do effective and convincing
           | science and simulation now is ... "a lot of simple tricks and
           | nonsense."
        
             | londons_explore wrote:
             | I don't think it's a pipe dream from an 'amount of compute'
             | perspective.
             | 
             | Any competent person can simulate 100 atoms in a crystal of
             | some material, and say "whoa, it seems the bulk of this
             | material behaves like a spring with f=kx, lets replace the
             | individual atom simulation with a bulk simulation which is
             | computationally far cheaper".
             | 
             | I don't see why AI couldn't do the same.
        
         | diggan wrote:
         | I don't think it's a "problem" as much as it is a "tradeoff".
         | You basically have two approaches to take here: 1) try to
         | simulate as best as you can, iteratively improve the simulation
         | space after trying it out in real-life, and go back and forth
         | or 2) skip the simulation step and do the same process but only
         | in real-life, not having any simulation step at all and only
         | rely on real scenarios, but few of them.
         | 
         | Considering how fast you can go with simulations vs real
         | launches, I'm not surprised the took the first approach.
        
         | 1W6MIC49CYX9GAP wrote:
         | Accurate simulation is also an AI problem, but that should be a
         | separate paper
        
         | theptip wrote:
         | > A fundamental problem with this entire class of machine
         | learning is that it is based on a model / simulation of
         | reality... all such simulations that attempt to model any non-
         | trivial system are imperfect
         | 
         | Depends on what your goal is. If you are trying to solve the
         | narrow problem of rocketry or whatever, sure. But maybe not if
         | your goal is making models smarter.
         | 
         | The broader context is that we need new oracles beyond math and
         | programming in order to exercise CoT models on longer planning-
         | horizon tasks.
         | 
         | In this case, if working with a toy world model lets you learn
         | generalizable strategies (I bet it does, as video games do too)
         | then this sort of eval can be a useful addition.
        
       | rel_ic wrote:
       | I think doing stuff like this probably has more downsides than
       | upsides.
        
       | FilosofumRex wrote:
       | Established engineering firms are trying to incorporate LLMs into
       | their fancy simulation software, but that's counterproductive,
       | just like professors who use LLMs to write new textbooks!
       | 
       | We need innovative disruptors to train LLMs to do engineering
       | from ground up and to make calls to simulation software/routines
       | when they need specialized/unique datapoints.
        
       ___________________________________________________________________
       (page generated 2025-05-02 23:02 UTC)