[HN Gopher] Testing Generative AI for Circuit Board Design
       ___________________________________________________________________
        
       Testing Generative AI for Circuit Board Design
        
       Author : DHaldane
       Score  : 206 points
       Date   : 2024-06-21 16:16 UTC (6 hours ago)
        
 (HTM) web link (blog.jitx.com)
 (TXT) w3m dump (blog.jitx.com)
        
       | bottlepalm wrote:
       | It'd be interesting to see how Sonnet 3.5 does at this. I've
       | found Sonnet a step change better than Opus, and for a fraction
       | of the cost. Opus for me is already far better than GPT-4. And
       | same as the poster found, GPT-4o is plain worse at reasoning.
       | 
       | Edit: Better at chain of thought, long running agentic tasks,
       | following rigid directions.
        
         | stavros wrote:
         | Opus is better than GPT-4? I've heard mixed experiences.
        
           | imperio59 wrote:
           | That's because the sample size is probably small and for
           | niche prompts or topics.
           | 
           | It's very hard to evaluate whether a model is better than
           | another, especially doing it in a scientifically sound way is
           | time consuming and hard.
           | 
           | This is why I find these types of comments like "model X is
           | so much better than model Y" to be about as useful as
           | "chocolate ice cream is so much better than vanilla"
        
             | r2_pilot wrote:
             | And both flavors have a base flavor of excrement... Still,
             | since I started using Claude 3 Opus (and now 3.5 Sonnet) a
             | couple of months back, I don't see myself switching from
             | them nor stopping use of LLM-based AI tech; it's just made
             | me feel like the computer is actually working for and with
             | me and even that alone can be enough to get me motivated
             | and accomplish what I set out to do.
        
               | skapadia wrote:
               | "it's just made me feel like the computer is actually
               | working for and with me and even that alone can be enough
               | to get me motivated and accomplish what I set out to do."
               | 
               | This is a great way to describe what I've been feeling /
               | experiencing as well.
        
             | stavros wrote:
             | True, I just tried it for generating a book summary, and
             | Sonnet 3.5 was very bad. GPT-4o is equally bad at that ,
             | gpt-4-turbo is great.
        
               | netsec_burn wrote:
               | This more likely has to do with context length?
        
               | stavros wrote:
               | No, all the information is there, but gpt-4o tends to
               | produce bullet points
               | (https://www.thesummarist.net/summary/the-making-of-a-
               | manager...), whereas gpt-4-turbo tends to produce much
               | more readable prose (https://www.thesummarist.net/summary
               | /supercommunicators/the-...).
        
           | DHaldane wrote:
           | It really depends on the type of question, but generally I'm
           | between Gemini and Claude these days for most things.
        
         | DHaldane wrote:
         | That's an interesting question - I'll take a few pokes at it
         | now to see if there's improvement.
        
           | DHaldane wrote:
           | Update: Sonnet 3.5 is better than any other model for the
           | circuit design and part finding tasks. Going to iterate a bit
           | on the prompts to see how much I can push the new model on
           | performance.
           | 
           | Figures that any article written on LLM limits is immediately
           | out of date. I'll write an update piece to summarize new
           | findings.
        
             | CamperBob2 wrote:
             | That name threw me for a loop. 'Sonnet' already means
             | something to EEs ( https://www.sonnetsoftware.com/ ).
        
       | cjk2 wrote:
       | Ex EE here
       | 
       |  _> The AI generated circuit was three times the cost and size of
       | the design created by that expert engineer at TI. It is also
       | missing many of the necessary connections._
       | 
       | Exactly what I expected.
       | 
       | Edit: to clarify this is even below the expectations of a junior
       | EE who had a heavy weekend on the vodka.
        
         | shrimp_emoji wrote:
         | It's like a generated image with an eye missing but for
         | circuits. :D
        
           | cjk2 wrote:
           | AI proceeds to use 2n3904 as a thyristor.
           | 
           | AI happy as it worked the first 10ns of the cycle.
        
             | jeffreygoesto wrote:
             | Every natural Intelligence knows that you need to reach out
             | to a 2N3055 for heavy duty. ;)
        
         | FourierEnvy wrote:
         | Why do people think inserting an LLM into the mix will make it
         | better than just an evolutionary or reinforcement model
         | applied? Who cares if you can talk to it like a human?
        
           | Terr_ wrote:
           | Yeah, when the author was writing about that initial query
           | about delay-per-unit-length, I'm thinking: "This doesn't tell
           | us whether an LLM can apply the concepts, only whether
           | relevant text was included in its training data."
           | 
           | It's a distinction I fear many people will have trouble
           | keeping in-mind, faced with the misleading eloquence of LLM
           | output.
        
         | rzzzt wrote:
         | I read an article on evolutionary algorithm-based designs a
         | long time ago -- they are effectively indecipherable by humans
         | and rely on the imperfections of the very FPGA that they are
         | synthesized on, but work great otherwise.
         | 
         | - https://www.damninteresting.com/on-the-origin-of-circuits/
         | 
         | -
         | https://www.sciencedirect.com/science/article/abs/pii/S03784...
        
       | dindobre wrote:
       | Using neural networks to solve combinatorial or discrete problems
       | is a waste of time imo, but I'd be more than happy if somebody
       | could convince me of the opposite.
        
         | utkuumur wrote:
         | There are recent papers based on diffusion that perform quite
         | well. Here's an example of a recent paper
         | https://arxiv.org/pdf/2406.01661. I am also working on ML-based
         | CO. My approach has a close 1% gap on hard instances with
         | 800-1200 nodes and less than 0.1% for 200-300 nodes on Maximum
         | Cut, Minimum Independent Set, and Maximum Clique problems. I
         | think these are very promising times for neural network-based
         | discrete optimization.
        
           | dindobre wrote:
           | Thanks, will try to give it a read this weekend. Would you
           | say that diffusion is the architectural change that opened up
           | CO for neural nets? Haven't followed this particular niche in
           | a while
        
       | HanClinto wrote:
       | This feels like an excellent demonstration of the limitation of
       | zero-shot LLMs. It feels like the wrong way to approach this.
       | 
       | I'm no expert in the matter, but for "holistic" things (where
       | there are a lot of cross-connections and inter-dependencies) it
       | feels like a diffusion-based generative structure would be
       | better-suited than next-token-prediction. I've felt this way
       | about poetry-generation, and I feel like it might apply in these
       | sorts of cases as well.
       | 
       | Additionally, this is a highly-specialized field. From the
       | conclusion of the article:
       | 
       | > Overall we have some promising directions. Using LLMs for
       | circuit board design looks a lot like using them for other
       | complex tasks. They work well for pulling concrete data out of
       | human-shaped data sources, they can do slightly more difficult
       | tasks if they can solve that task by writing code, but eventually
       | their capabilities break down in domains too far out of the
       | training distribution.
       | 
       | > We only tested the frontier models in this work, but I predict
       | similar results from the open-source Llama or Mistral models.
       | Some fine tuning on netlist creation would likely make the
       | generation capabilities more useful.
       | 
       | I agree with the authors here.
       | 
       | While it's nice to imagine that AGI would be able to generalize
       | skills to work competently in domain-specific tasks, I think this
       | shows very clearly that we're not there yet, and if one wants to
       | use LLMs in such an area, one would need to fine-tune for it.
       | Would like to see round 2 of this made using a fine-tuning
       | approach.
        
         | DHaldane wrote:
         | My gut agrees with you that LLMs shouldn't do this well on a
         | specialty domain.
         | 
         | But I think there's also the bitter lesson to be learned here:
         | many times people say LLMs won't do well on a task, they are
         | often surprised either immediately or a few months later.
         | 
         | Overall not sure what to expect, but fine tuning experiments
         | would be interesting regardless.
        
           | cjk2 wrote:
           | I doubt it'd work any better. Most of EE time I have spent is
           | swearing at stuff that looked like it'd work on paper but
           | didn't due to various nuances.
           | 
           | I have my own library of nuances but how would you even fine
           | tune anything to understand the black box abstraction of an
           | IC to work out if a nuance applies or not between it and a
           | load or what a transmission line or edge would look like
           | between the IC and the load?
           | 
           | This is where understanding trumps generative AI instantly.
        
             | DHaldane wrote:
             | I doubt it too, but I notice that I keep underestimating
             | the models.
             | 
             | Do you have a challenge task I can try? What's the easiest
             | thing I could get an LLM to do for circuit board design
             | that would surprise you?
        
               | cjk2 wrote:
               | Make two separate signals arrive at exactly the same time
               | on two 50 ohm transmission lines that start and end next
               | to each other and go around a right hand bend. At 3.8GHz.
               | 
               | Edit: no VSWR constraint. Can add that later :)
               | 
               | Edit 2: oh or design a board for a simple 100Mohm input
               | instrumentation amplifier which knows what a guard ring
               | is and how badly the solder mask will screw it up :)
        
               | bmicraft wrote:
               | It would seem to me that the majority of boards would be
               | a lot more forgiving. Are you saying you wouldn't be
               | impressed if it could do only say 70% of board designs
               | completely?
        
               | AdamH12113 wrote:
               | Not the GP, but as an EE I can tell you that the majority
               | of boards are not forgiving. One bad connection or one
               | wrong component often means the circuit just doesn't
               | work. One bad footprint often means the board is
               | worthless.
               | 
               | On top of that, making an AI that can regurgitate simple
               | textbook circuits and connect them together in reasonable
               | ways is only the first step towards a much more difficult
               | goal. More subtle problems in electronics design are all
               | about context-dependent interactions between systems.
        
               | nurple wrote:
               | I hate that this is true. I think ML itself could be
               | applied to the problem to help you catch mistakes in
               | realtime, like language servers in software eng.
               | 
               | I have experience building boards in Altium and found it
               | rather enjoyable; my own knowledge was often a constraint
               | as I started out, but once I got proficient it just
               | seemed to flow out onto the canvas.
               | 
               | There are some design considerations that would be
               | awesome to farm out to genai, but I think we are far from
               | that. Like stable-diffusion is to images, the source data
               | for text-to-PCB would need to be well-labeled in addition
               | to being correllated with the physical PCB features
               | themselves.
               | 
               | The part where I think we lose a lot of data in pursuit
               | of something like this, is all of the research and
               | integration work that went on behind everything that
               | eventually got put into the schematic and then laid out
               | on a board. I think it would be really difficult to
               | "diffuse" a finished PCB from an RFQ-level description.
        
               | cjk2 wrote:
               | No because it's hard enough picking up an experienced
               | human's designs and work with them. A 70% done board is a
               | headache to unwrap. I'd start again.
        
               | nurple wrote:
               | This is how I am with software. There's usually a reason
               | I'm arriving at 70% done, and it's not often because it's
               | well designed and documented...
        
               | DHaldane wrote:
               | Right - LLMs would be a bit silly for these cases. Both
               | overkill and underkill. Current approach for length
               | matching is throw it off to a domain specific solver.
               | Example test-circuit:
               | https://x.com/DuncanHaldane/status/1803210498009342191
               | 
               | How exact is exactly the same time? Current solver
               | matches to under 10fs, and I think at that level you'd
               | have to fab it to see how close you get with fiber weave
               | skew and all that.
               | 
               | Do you have a test case for a schematic design task?
        
               | cjk2 wrote:
               | Yeah. But you need $200k worth of Keysight kit to test
               | it.
               | 
               | The point is there's a methodology to solve these
               | problems already. Is this better? And can it use and
               | apply it?
        
             | LeifCarrotson wrote:
             | Really? Most of the time?
             | 
             | I find I spend an enormous amount of time on boring stuff
             | like connecting VCC and ground with appropriate decoupling
             | caps, tying output pins from one IC to the input pins on
             | the other, creating library parts from data sheets, etc.
             | 
             | There's a handful of interesting problems in any good
             | project where the abstraction breaks down and you have to
             | prove your worth. But a ton of time gets spent on the
             | equivalent of boilerplate code.
             | 
             | If I could tell an AI to generate a 100x100 prototype with
             | such-and-such a microcontroller, this sensor and that
             | sensor with those off-board connectors, with USB power, a
             | regulator, a tag-connect header, a couple debug LEDs, and
             | break out unused IO to a header...that would have huge
             | value to my workflow, even if it gave up on anything analog
             | or high-speed. Presumably you'd just take the first pass
             | schematic/board file from the AI and begin work on anything
             | with nuance.
             | 
             | If generative AI can do equivalent work for PCBs as it can
             | do for text programming languages, people wouldn't use it
             | for transmission line design. They'd use it for the
             | equivalent of parsing some JSON or making a new class with
             | some imports, fields, and method templates.
        
               | scld wrote:
               | "Looks like you forgot pullups on your i2c lines" would
               | be worth a big monthly subscription hahaha.
        
               | oscillonoscope wrote:
               | There are schematic analysis tools which do that now just
               | based on the netlist
        
               | DHaldane wrote:
               | I've found that for speeding up design generation like
               | that, most of the utility comes from the coding approach.
               | 
               | AI can't do it itself (yet), and having it call the
               | higher level functions doesn't save that much time...
        
           | sweezyjeezy wrote:
           | Some research to the contrary [1] - tldr is that they didn't
           | find evidence that generative models really do zero shot well
           | at all yet, if you show it something it literally hasn't seen
           | before, it isn't "generally intelligent" enough to do it
           | well. This isn't an issue for a lot of use-cases, but does
           | seem to add some weight to the "giga-scale memorization"
           | hypothesis.
           | 
           | [1] https://arxiv.org/html/2404.04125v2
        
           | HanClinto wrote:
           | > But I think there's also the bitter lesson to be learned
           | here: many times people say LLMs won't do well on a task,
           | they are often surprised either immediately or a few months
           | later.
           | 
           | Heh. This is very true. I think perhaps the thing I'm most
           | amazed by is that simple next-token prediction seems to work
           | unreasonably well for a great many tasks.
           | 
           | I just don't know how well that will scale into more complex
           | tasks. With simple next-token prediction there is little
           | mechanism for the model to iterate or to revise or refine as
           | it goes.
           | 
           | There have been some experiments with things like speculative
           | generation (where multiple branches are evaluated in
           | parallel) to give a bit of a lookahead effect and help avoid
           | the LLM locking itself into dead-ends, but they don't seem
           | super popular overall -- people just prefer to increase the
           | power and accuracy of the base model and keep chugging
           | forward.
           | 
           | I can't help feeling like a fundamental shift something more
           | akin to a diffusion-based approach would be helpful for such
           | things. I just want some sort of mechanism where the model
           | can "think" longer about harder problems. If you present a
           | simple chess board to an LLM or a complex board to an LLM and
           | ask it to generate the next move, it always responds in the
           | same amount of time. That alone should tell us that LLMs are
           | not intelligent, and they are not "thinking", and they will
           | be insufficient for this going forward.
           | 
           | I believe Yann LeCun is right -- simply scaling LLMs is not
           | going to get us to AGI. We need a fundamental structural
           | shift to something new, but until we stop seeing such insane
           | advancements in the quality of generation with LLMs (looking
           | at you, Claude!!), I don't think we will move beyond. We have
           | to get bored with LLMs first.
        
             | pton_xd wrote:
             | > If you present a simple chess board to an LLM or a
             | complex board to an LLM and ask it to generate the next
             | move, it always responds in the same amount of time.
             | 
             | Is that true, especially if you ask it to think step-by-
             | step?
             | 
             | I would think the model has certain associations for
             | simple/common board states and different ones for
             | complex/uncommon states, and when you ask it to think step-
             | by-step it will explain the associations with a particular
             | state. That "chattiness" may lead it to using more
             | computation for complex boards.
        
               | HanClinto wrote:
               | > > If you present a simple chess board to an LLM or a
               | complex board to an LLM and ask it to generate the next
               | move, it always responds in the same amount of time.
               | 
               | > Is that true, especially if you ask it to think step-
               | by-step?
               | 
               | That's fair -- there's a lot of room to grow in this
               | area.
               | 
               | If the LLM has been trained to operate with running
               | internal-monologue, then I believe they will operate
               | better. I think this definitely needs to be explored more
               | -- from what little I understand of this research, the
               | results are sporadically promising, but getting something
               | like ReAct (or other, similar structures) to work
               | consistently is something I don't think I've seen yet.
        
             | visarga wrote:
             | > I just want some sort of mechanism where the model can
             | "think" longer about harder problems.
             | 
             | There is such a mechanism - multiple rounds of prompting.
             | You can implement diverse patterns (chains, networks) of
             | prompts.
        
           | anonymoushn wrote:
           | We have 0 y/o/y progress on Advent of Code, for example.
           | Maybe we'll have some progress 6 months from now :)
           | https://www.themotte.org/post/797/chatgpt-vs-advent-of-code
        
             | DHaldane wrote:
             | Have you tried using more 4000x more samples?
             | 
             | https://redwoodresearch.substack.com/p/getting-50-sota-on-
             | ar...
        
         | eimrine wrote:
         | I like how you called it holistic, it is maybe the first time I
         | see this word not in a "bad" context.
         | 
         | What about the topic, it is impossible to synthesize STEM
         | things not in the manner an engineer does this. I mean thou
         | shalt to know some typical solutions and have all the
         | calculations for all what's happening in the schematic being
         | developed.
         | 
         | Textbooks are not a joke and no matter who are you - a human or
         | a device.
        
         | omgJustTest wrote:
         | I asked this question of Duncan Dec 22!
         | 
         | If you are interested I highly recommend this + your favorite
         | llm. It does not do everything but is far superior to some
         | highly expensive tools, in flexibility and repeatability.
         | https://github.com/devbisme/skidl
        
           | HanClinto wrote:
           | This tool looks really powerful, thanks for the link!
           | 
           | One thing I've been personally really intrigued by is the
           | possibility of using self-play and adversarial learning as a
           | way to advance beyond our current stage of imitation-only
           | LLMs.
           | 
           | Having a strong rules-based framework to be able to be able
           | to measure quality and correctness of solutions is necessary
           | for any RL training setup to proceed. I think that skidl
           | could be a really nice framework to be part of an RL-trained
           | LLM's curriculum!
           | 
           | I've written down a bunch of thoughts [1] on using games or
           | code-generation in an adversarial training setup, but I could
           | see circuit design being a good training ground as well!
           | 
           | * [1] https://github.com/HanClinto/MENTAT
        
         | hoosieree wrote:
         | I agree diffusion makes more sense for optimizing code-like
         | things. The tricky part is coming up with a reasonable set of
         | "add noise" transformations.
        
           | HanClinto wrote:
           | > The tricky part is coming up with a reasonable set of "add
           | noise" transformations.
           | 
           | Yes, as well as dealing with a variable-length window.
           | 
           | When generating images with diffusion, one specifies the
           | image ahead-of-time. When generating text with diffusion,
           | it's a bit more open-ended. How long do we want this
           | paragraph to go? Well, that depends on what goes into it --
           | so how do we adjust for that? Do we use a hierarchical tree-
           | structure approach? Chunk it and do a chain of overlapping
           | segments that are all of fixed-length (could possibly be
           | combined with a transformer model)?
           | 
           | Hard to say what would finally work in the end, but I think
           | this is the sort of thing that YLC is talking about when he
           | encourages students to look beyond LLMs. [1]
           | 
           | * [1] https://x.com/ylecun/status/1793326904692428907
        
         | surfingdino wrote:
         | > This feels like an excellent demonstration of the limitation
         | of zero-shot LLMs. It feels like the wrong way to approach
         | this.
         | 
         | There is one posted on HN every week. How many more do we need
         | to accept the fact this tech is not what it is sold at and we
         | are bored waiting for it get good? I am not say "get better",
         | because it keeps getting better, but somehow doesn't get good.
        
           | makk wrote:
           | That's a perception and the problem isn't the AI it's human
           | nature: 1. every time AI is able to do a thing we move the
           | goalposts and say, yeah, but it can't do that other thing
           | over there; 2. We are impatient, so our ability to get bored
           | tends to outpace the rate of change.
        
             | slg wrote:
             | I don't think the problem is moving the goalposts, but
             | rather there are no actual goalposts. Advocates for this
             | technology imply it can do anything either because they
             | believe it will be true in the near future or they just
             | want others to believe it for a wide range of reasons
             | including to get rich of it. Therefore the general public
             | has no real idea what the ideal use cases are for this
             | technology in its current state so they keep asking it to
             | do stuff it can't do well. It is really no different than
             | the blockchain in that regard.
        
             | goatlover wrote:
             | The other side of this coin is everyone overhyping what AI
             | can do, and when the inevitable criticism comes, they
             | respond by claiming the goal posts are being moved.
             | Perhaps, but you also told me it could do XYZ, when it can
             | only do X and some Y, but not much Z, and it's still not
             | general intelligence in the he broad sense.
        
               | refulgentis wrote:
               | I appreciate this comment because I think it really
               | demonstrates the core problem with what I'll call the
               | "get off my lawn >:|" argument, because it's avowedly
               | about personal emotions.
               | 
               | It's not "general intelligence", so it's over hyped, and
               | They get so whiny about the inevitable criticism, and
               | They are ignoring that it's so mindnumbingly boring to
               | have people making the excuse that "designed a circuit
               | board from scratch" wasn't something anyone thinks or
               | claims an LLM should do.
               | 
               | Who told you LLMs can design circuit boards?
               | 
               | Who told you LLMs are [artificial] general intelligence?
               | 
               | I get sick of it constantly being everywhere, but I don't
               | feel the need to intellectualize it in a way that blames
               | the nefarious ???
        
               | ben_w wrote:
               | > Who told you LLMs are [artificial] general
               | intelligence?
               | 
               | *waves*
               | 
               | Everyone means a different thing by each letter of AGI,
               | and sometimes also by the combination.
               | 
               | I know my opinion is an unpopular one, but given how much
               | more general-purpose they are than most other AI, I count
               | LLMs as "general" AI; and I'm old enough to remember when
               | AI didn't automatically mean "expert level or better",
               | when it was a _surprise_ that Kasparov was beaten (let
               | alone Lee Sedol).
               | 
               | LLMs are (currently) the ultimate form of "Jack of all
               | trades, master of none".
               | 
               | I'm not surprised that it failed with these tests, even
               | though it clearly knows more about electronics than me.
               | (I once tried to buy a 220 k resistor, didn't have the
               | skill to notice the shop had given me a 220 O resistor,
               | the resistor caught fire).
               | 
               | I'd still _like_ to call these things  "AGI"... except
               | for the fact that people don't agree on what the word
               | means and keep objecting to my usage of the initials as
               | is, so it would't really communicate anything for me to
               | do so.
        
               | derefr wrote:
               | ML scientists will tell you it can do X and some Y but
               | not much Z. But the public doesn't listen to ML
               | scientists. Most of what the public hears about AI comes
               | from businessmen trying to market a vision to investors
               | -- a vision, specifically, of what _their business_ will
               | be capable of _five years from bow_ given _predicted
               | advancements in AI capabilities in the mean time_ ; which
               | has roughly nothing to do with what current models can
               | do.
        
           | exe34 wrote:
           | how long does it take for a child to start doing surgery?
           | publishing novel theorems? how long has the humble
           | transformer been around?
        
             | ben_w wrote:
             | Wall-clock or subjective time?
             | 
             | I think it would take a human about 2.6 million (waking)
             | years to actually _read_ Common Crawl[0]; though obviously
             | faster if they simply absorb token streams as direct
             | sensory input.
             | 
             | The strength of computers is that transistors are
             | (literally) faster than synapses to the degree to which
             | marathon runners are faster than continental drift; the
             | weakness is they need to, too -- current generation AI is
             | only able to be this good due to this advantage allowing it
             | to read far more than any human.
             | 
             | How much this difference matters depends on the use-case:
             | if AI were as good at learning as we are, Tesla's FSD would
             | be level 5 autonomy years ago already, even with just
             | optical input.
             | 
             | [0] April 2024: 386 TiB; assuming 9.83 bits per word and
             | 250 w.p.m: https://www.wolframalpha.com/input?i=386+TiB+%2F
             | +9.83+bits+p...
        
               | TeMPOraL wrote:
               | Subjective time doesn't really matter unless something is
               | experiencing it. It could be 2.6 million years, but if
               | the wall-clock time is half a year, then great - we've
               | managed to brute-force some degree of intelligence in
               | half a year! And we're at the beginning of this journey;
               | there surely are many things to optimize that will
               | decrease both wall-clock and subjective training time.
               | 
               | As the saying goes - "make it work, make it right, make
               | it fast".
        
           | echelon wrote:
           | I'm in awe of the progress in AI images, music, and video.
           | This is probably where AI shines the most.
           | 
           | Soon everything you see and hear will be built up through a
           | myriad of AI models and pipelines.
        
             | slg wrote:
             | > Soon everything you see and hear will be built up through
             | a myriad of AI models and pipelines.
             | 
             | It is so bizarre that some people view this as a positive
             | outcome.
        
             | goatlover wrote:
             | I sincerely hope not. Talk about a dystopian future. That's
             | even worse than what social media has become.
        
             | ben_w wrote:
             | They already are, when using the meaning of "AI" that I
             | grew up with.
             | 
             | The Facebook feed is AI; Google PageRank is AI; anti-spam
             | filters are AI; A/B testing is AI; recommendation systems
             | are AI.
             | 
             | It's been a long time since computers took over from humans
             | with designing transistor layouts in CPUs -- I was hearing
             | about the software needing to account for quantum mechanics
             | nearly a decade ago already.
        
           | refulgentis wrote:
           | There's this odd strain of thought that there's some general
           | thing that will pop for hucksters and the unwashed masses,
           | who are sheep led along by huckster wolves who won't admit
           | LLMs aint ???, because they're profiting off it
           | 
           | It's frustrating because it's infantalizing, it derails the
           | potential of an interesting technical discussion (ex. Here,
           | diffusion), and it misses the mark substantially.
           | 
           | At the end of the day, it's useful in a thousand ways day to
           | day, and the vast majority of people feel this way. The only
           | people I see vehemently arguing the opposite seem to assume
           | only things with 0 error rate are useful or are upset about
           | money in some form.
           | 
           | But is that really it? I'm all ears. I'm on a 5 hour flight.
           | I'm genuinely unclear on whats going on that leads people to
           | take this absolutist position that they're waiting for ??? to
           | admit ??? about LLMs.
           | 
           | Yes, the prose machine didnt nail circuit design, that
           | doesn't mean whatever They you're imagining needs to give up
           | and accept ???
        
             | ben_w wrote:
             | > But is that really it? I'm all ears. I'm on a 5 hour
             | flight. I'm genuinely unclear on whats going on that leads
             | people to take this absolutist position that they're
             | waiting for ??? to admit ??? about LLMs.
             | 
             | Irony: humans think in very black-and-white terms, one
             | could even say boolean; conversely LLMs display subtly and
             | nuance.
             | 
             | When I was a kid, repeats of Trek had Spock and Kirk
             | defeating robots with the liar's paradox, yet today it
             | seems like humans are the ones who are broken by it while
             | the machines are just going "I understood that reference!"
        
               | refulgentis wrote:
               | Excellent point, it really is what it comes down to.
               | There's people getting hoodwinked and people hoodwinking
               | and then me, the one who sees them for what they are.
        
               | goatlover wrote:
               | And yet we still don't have Data or the Holographic
               | Doctor.
        
               | ben_w wrote:
               | You're demonstrating my point :)
               | 
               | When we get to that level, we're all out of work.
               | 
               | In the meantime, LLMs are already basically as good as
               | the scriptwriters made the TNG-VOY era starship computers
               | act.
        
             | shermantanktop wrote:
             | So what should we make of the presence of actual hucksters
             | and actual senior execs who are acting like credulous
             | sheep? I see this every day in my world.
             | 
             | At the same time I do appreciate the actual performance and
             | potential future promise of this tech. I have to remind
             | myself that the wolf and sheep show is a side attraction,
             | but for some people it's clearly the main attraction.
        
               | wruza wrote:
               | Why should we even?
               | 
               | The problem with everything today is not only that it's
               | hype-centric, but that that carries away those who were
               | otherwise reasonable. AI isn't any special in this
               | regard, it's just "crypto" of this decade.
               | 
               | I see this trend everywhere, in tech, socio, markets.
               | Everything is way too fake, screamy and blown out of
               | proportion.
        
               | refulgentis wrote:
               | The wolves/sheep thing was to indicate how moralizing and
               | infantalizing serves as a substitute for actually
               | explaining what the problem is, because surely, it's not
               | that the prose machine isn't doing circuit design.
               | 
               | I'm sure you see it, I'd just love for someone to pause
               | their internal passion play long enough to explain what
               | they're seeing. Because I refuse to infantalize, I refuse
               | to believe it's just grumbling because its not 100%
               | accurate 100% of the time, and doesn't do 100% of
               | everything.
        
               | shermantanktop wrote:
               | I am literally right now explaining to a senior exec why
               | some PR hype numbers about developer productivity from
               | genAI are not comparable to internal numbers, because he
               | is hoping to say to his bosses that we're doing better
               | than others. This is a smart, accomplished person, but he
               | can read the tea leaves.
               | 
               | The problem with hype is that it can become a
               | pathological form of social proof.
        
               | photonthug wrote:
               | I'll play along. The thing that's annoying me lately is
               | that session details leaking between chats has been
               | enabled as a "feature", which is quickly making ChatGPT
               | more like the search engine and social media echo
               | chambers that I think lots of us want to escape. It's
               | also harmful for the already slim chances of having
               | reproducible / deterministic results, which is bad since
               | we're using these things for code generation as well as
               | rewriting emails and essays or whatever.
               | 
               | Why? Is this naive engineering refusing to acknowledge
               | the same old design flaws? Nefarious management fast
               | tracking enshittification? Or do users actually want
               | their write-a-naughty-limerick goofs to get mixed up with
               | their serious effort to fast track circuit design? I
               | wouldn't want to appear cynical but one of these
               | explanations just makes more sense than the others!
               | 
               | The core tech such as it is is fine, great even. But it's
               | not hard to see many different ways that it's already
               | spiraling out of control.
        
         | yousif_123123 wrote:
         | One downside for diffusion based systems (and I'm very noob in
         | this) is that the model won't be able to see it's input and
         | output in the same space, therefore wouldn't be able to do
         | follow-up instructions to fix things or improve on it. Where as
         | an LLM generating html could follow instructions to modify it
         | as well. It's input and output are the same format.
        
       | guidoism wrote:
       | This reminds me of my professor's (probably very poor)
       | description of NP-complete problems where the computer would
       | provide an answer that may or may not be correct and you just had
       | to check that it was correct and you do test for correctness in
       | polynomial time.
       | 
       | It kind of grosses me out that we are entering a world where
       | programming could be just testing (to me) random permutations of
       | programs for correctness.
        
         | moffkalast wrote:
         | Well we had to keep increasing inefficiency somehow, right?
         | Otherwise how would Wirth's law continue to hold?
        
       | cushychicken wrote:
       | I'm terrified that JITX will get into the LLM / Generative AI for
       | boards business. (Don't make me homeless, Duncan!)
       | 
       | They are already far ahead of many others with respect to next
       | generation EE CAD.
       | 
       | Judicious application of AI would be a big win for them.
       | 
       | Edit: adding "TL;DRN'T" to my vocabulary XD
        
         | DHaldane wrote:
         | I promise that we want to stay a software company that helps
         | people design things!
         | 
         | Adding Skynetn't to company charter...
        
       | AdamH12113 wrote:
       | The conclusions are very optimistic given the results. The LLMs:
       | 
       | * Failed to properly understand and respond to the requirements
       | for component selection, which were already pretty generic.
       | 
       | * Succeeded in parsing the pinout for an IC but produced an
       | incomplete footprint with incorrect dimensions.
       | 
       | * Added extra components to a parsed reference schematic.
       | 
       | * Produced very basic errors in a description of filter
       | topologies and chose the wrong one given the requirements.
       | 
       | * Generated utterly broken schematics for several simple
       | circuits, with missing connections and aggressively-incorrect
       | placement of decoupling capacitors.
       | 
       | Any one of these failures, individually, would break the entire
       | design. The article's conclusion for this section buries the lede
       | slightly:
       | 
       | > The AI generated circuit was three times the cost and size of
       | the design created by that expert engineer at TI. It is also
       | missing many of the necessary connections.
       | 
       | Cost and size are irrelevant if the design doesn't work. LLMs
       | aren't a third as good as a human at this task, they just fail.
       | 
       | The LLMs do much better converting high-level requirements into
       | (very) high-level source code. This make sense (it's
       | fundamentally a language task), but also isn't very useful.
       | Turning "I need an inverting amplifier with a gain of 20" into
       | "amp = inverting_amplifier('amp1', gain=-20.0)" is pretty
       | trivial.
       | 
       | The fact that LLMs apparently perform better if you literally
       | offer them a cookie is, uh... something.
        
         | lemonlime0x3C33 wrote:
         | thank you for summarizing the results, I feel much better about
         | my job security. Now if AI could make a competent auto router
         | for fine pitch BGA components that would be really nice :)
        
         | neltnerb wrote:
         | I think the only bit that looked handy in there would be if it
         | could parse PDF datasheets and help you sort them by some
         | hidden parameter. If I give it 100 datasheets for microphones
         | it really should be able to sort them by mechanical height.
         | Maybe I'm too optimistic.
         | 
         | The number of times I've had to entirely redo a circuit because
         | of one misplaced connection, yeah, none of those circuits
         | worked for any price before I fixed every single error.
        
           | DHaldane wrote:
           | Agree that PDF digesting was the most useful.
           | 
           | I think Gemini could definitely do that microphone study.
           | Good test case! I remember spending 8 hours on DigiKey in the
           | bad old times, looking for an audio jack that was 0.5mm
           | shorter.
        
             | hadlock wrote:
             | As I understand it, PDF digestion/manipulation (and
             | particularly translation) has long been a top request from
             | businesses, based on conversations I've had with people
             | selling the technology, so it doesn't surprise me that
             | Gemini excels at this task.
        
             | robxorb wrote:
             | Anyone looking for an idea for something potentially
             | valuable to make: ingest PDF datasheets and let us
             | search/compare etc, across them. The PDF datasheet is
             | possibly one of the biggest and most unecessary hurdles to
             | electronics design efficiency.
        
         | doe_eyes wrote:
         | Yes, this seemed pretty striking to me: the author clearly
         | _wanted_ the LLM to perform well. They started with a problem
         | for which solutions are pretty much readily available on the
         | internet, and then provided a pretty favorable take on the
         | model 's mistakes.
         | 
         | But the bottom line is that it's a task that a novice could
         | have solved with a Google search or two, and the LLM fumbled it
         | in ways that'd be difficult for a non-expert to spot and
         | rectify. LLMs are generally pretty good at information
         | retrieval, so it's quite disappointing.
         | 
         | The cookie thing... well, they learn statistical patterns.
         | People on the internet often try harder if there is a quid-pro-
         | quo, so the LLMs copy that, and it slips past RLHF because
         | "performs as well with or without a cookie" is probably not one
         | of the things they optimize for.
        
         | oscillonoscope wrote:
         | I don't know enough about LLMs to understand if its feasible or
         | not but it seems like it would be useful to make certain tasks
         | hard-coded or add some fundamental constraints on it. Like when
         | making footprints, it should always check that the number of
         | pads is never less than the number of schematic symbol pins.
         | Otherwise, the AI just feels like your worst coworker
        
       | sehugg wrote:
       | How does this compare to Flux.ai?
       | https://docs.flux.ai/tutorials/ai-for-hardware-design
        
         | built_with_flux wrote:
         | flux.ai founder here
         | 
         | Agree with OP that the raw models aren't that useful for
         | schematic/pcb design.
         | 
         | It's why we build flux from the ground up to provide the models
         | with the right context. The models are great moderators but
         | poor sources of great knowledge.
         | 
         | Here are some great use cases:
         | 
         | https://www.youtube.com/watch?v=XdH075ClrYk
         | 
         | https://www.youtube.com/watch?v=J0CHG_fPxzw&t=276s
         | 
         | https://www.youtube.com/watch?v=iGJOzVf0o7o&t=2s
         | 
         | and here a great example of levering AI to go from idea to full
         | design https://x.com/BuildWithFlux/status/1804219703264706578
        
       | shrubble wrote:
       | Reminds me of this, an earlier expert-system method for CPU
       | design, which was not used in subsequent designs for some reason:
       | https://en.wikipedia.org/wiki/VAX_9000#SID_Scalar_and_Vector...
        
       | surfingdino wrote:
       | Look! You can design thousands of shit appliances at scale! /s
        
       | Terr_ wrote:
       | To recycle a rant, there's a whole bunch of hype and investor
       | money riding on a very questionable idea here, namely:
       | 
       | "If we make a _really really good_ specialty text-prediction
       | engine, it could be able to productively mimic an imaginary
       | general AI, and if it can do that then it can productively mimic
       | _other_ specialty AIs, because it 's all just intelligence,
       | right?"
        
         | ai4ever wrote:
         | investor money is seduced by the possibilities and many of the
         | investors are in it for FOMO.
         | 
         | few really understand what the limits of the tech are. and if
         | it will even unlock the usecases for which it is being touted.
        
       | seveibar wrote:
       | I work on generative AI for circuit board design with tscircuit,
       | IMO it's definitely going to be the dominant form of
       | bootstrapping or combining circuit designs in the near future (<5
       | years)
       | 
       | Most people are wrong that AI won't be able to do this soon. The
       | same way you can't expect an AI to generate a website in
       | assembly, but you CAN expect it to generate a website with
       | React/tailwind, you can't expect an AI to generate circuits
       | without having strong functional blocks to work with.
       | 
       | Great work from the author studying existing solutions/models-
       | I'll post some of my findings soon as well! The more you play
       | with it, the more inevitable it feels!
        
         | HanClinto wrote:
         | I'd be interested in reading more of your findings!
         | 
         | Are you able to accomplish this with prompt-engineering, or are
         | you doing fine-tuning of LLMs / custom-trained models?
        
           | seveibar wrote:
           | No fine tuning needed, as long as the target language/DSL is
           | fairly natural, just give eg a couple examples of tscircuit
           | React, atopile JotX etc and it can generate compliant
           | circuits. It can hallucinate imports, but if you give it an
           | import list you can improve that a lot.
        
         | maccard wrote:
         | > The same way you can't expect an AI to generate a website in
         | assembly, but you CAN expect it to generate a website with
         | React/tailwind
         | 
         | Can you? Because last time I tried (probably about February) it
         | still wasn't a thing
        
       | blueyes wrote:
       | See Quilter: https://www.quilter.ai
        
       | kristopolous wrote:
       | Just the other day I came up with an idea of doing a flatbed scan
       | of a circuit board and then using machine learning and a bit of
       | text promoting to get to a schematic
       | 
       | I don't know how feasible it is. This would probably take low
       | $millions or so of training, data collection and research to get
       | not trash results.
       | 
       | I'd certainly love it for trying to diagnose circuits.
       | 
       | It's probably not really that possible even at higher end
       | consumer grade 1200dpi.
        
         | cmbuck wrote:
         | This would be an interesting idea if you were able to solve the
         | problem of inner layers. Currently to reverse engineer a board
         | with more than 2 layers an x-ray machine is required to glean
         | information about internal routing. Otherwise you're making
         | inferences based on surface copper only.
        
           | kristopolous wrote:
           | Maybe not. I scanned a bluetooth aux transceiver yesterday as
           | a test of how well a flatbed can pick up details. There's a
           | bunch of these on the market and the cheap ones, they are
           | more or less equivalent. It's a CSR 8365 based device, which
           | you can read from the scan. The industry is generally
           | convergent on the major design decisions for some hardware
           | purpose for some given time period.
           | 
           | And the devices, in this case, bluetooth aux transceivers,
           | they all do the same things. They've even more or less
           | converged on all being 3 buttons. When optimizing for cost
           | reduction with the commodity chips that everyone is using to
           | do the same things, the manufacturer variation isn't that
           | vast.
           | 
           | In the same way you can get 3d models from 2d photos because
           | you can identify the object based on a database of samples
           | and then guess the 3d contours, the hypothesis to test is
           | whether with enough scans and schematics, a sufficiently
           | large statistical model will be good enough to make decent
           | guesses.
           | 
           | If you've got say 40 devices with 80% of the same chips doing
           | the same things for the same purpose, a 41st device might
           | have lots of guessable things that you can't necessarily
           | capture on a cheap flatbed
           | 
           | This will _probably_ work but it 's a couple million away
           | from becoming a reality. There's shortcuts that might make
           | this a couple $100,000s project (essentially data contracts
           | with bespoke chip printers) but I'd have to make those
           | connections. And even then, it's just a hobbyist product. The
           | chances of recouping that investment is probably zero
           | although the tech would certainly be cool and useful. Just
           | not "I'll pay you money" level useful.
        
       | amelius wrote:
       | Can we have an AI that reads datasheets and produces Spice
       | circuits? With the goal of building a library of simulation
       | components.
        
         | klysm wrote:
         | That's the kind of thing where verification is really hard, and
         | things will look plausible even if incorrect.
        
       | ncrmro wrote:
       | I had it generate some opencad but never looked into it further.
        
       ___________________________________________________________________
       (page generated 2024-06-21 23:00 UTC)