[HN Gopher] ChatGPT for Hardware Design
___________________________________________________________________
ChatGPT for Hardware Design
Author : built_with_flux
Score : 151 points
Date : 2023-04-27 17:55 UTC (5 hours ago)
(HTM) web link (docs.flux.ai)
(TXT) w3m dump (docs.flux.ai)
| markwu2001 wrote:
| PCB Designer on the team:
|
| Holy cow this is awesome! The integration of project context with
| an LLM enabled more than the sum of its parts when it comes to
| information access.
|
| When designing circuits for fast iterations, you're constantly
| managing risk and time expenditure; this leads to copying a lot
| of "flight heritage" circuits so to speak.
|
| With the LLM, I'm able to get highly condensed starting points
| for better circuits when it comes to simplicity,
| understandability, or performance. As of right now, all I have to
| do is fact check the solution which is much easier than
| synthesizing one myself. I'm citing the example where I got it to
| design me a viable high gain analog frontend that meets my gain,
| bandwidth, noise, and biasing requirements.
| nullsense wrote:
| How often is it able to get it right first try?
| markwu2001 wrote:
| I'll interpret "right" as in giving correct information. I
| found that it depends on the type of question asked; if it's
| somewhat general information such as design concepts and
| design topologies, it impressively nails it 99% of the time
| for my limited testing period. The main area it gets things
| wrong relates to very specific information that has only one
| source: e.g. datasheet specs. I heard the team already has
| plans to mitigate hallucinations on this front.
|
| Also, I find myself having a conversation as I would with a
| real person, so it's less of spitting out the right answer
| for any technical question I might have, but more of a design
| buddy to consult when you're blocked on your search through
| the massive electronics solution space. Of course, this is a
| very preliminary use case and I can't wait to see what other
| people use it for.
| gfodor wrote:
| I've been interested in learning how to design PCBs, I wonder
| if this tech helps constrain the set of things one ought to
| focus on learning, with the assumption that AI can fill in
| other areas.
| markwu2001 wrote:
| I love teaching PCB design! As with you, I'm also really
| curious about AI's contributions to learning. My opinion is
| that the automation of search and execution increases the
| impact one person can make so more time can be spent on
| connecting the dots at a higher level. Whether or not
| education catches up in time is another story haha. It's
| pretty open ended right now but it's undeniable that a huge
| educational gap there.
| built_with_flux wrote:
| Here is nice demo video
|
| https://www.youtube.com/watch?v=5aCN92kOxTU
| greg wrote:
| Engineer on the team here. Some of the interesting challenges of
| doing ChatGPT for circuit design were:
|
| 1) How to communicate the circuit connections to ChatGPT in the
| text prompt. We ended up just using the standard netlist format.
| Apparently it knows about netlists from its training data. It
| also knows about datasheets.
|
| 2) How to get the needed accuracy and precision for questions
| like "calculate the resistance needed between component A and B".
| For that, we adopted the popular langchain framework to integrate
| specific "tools" into the AI for specific recognizable problems.
| joshuanapoli wrote:
| How do you deal with designs whose netlist or part list exceeds
| the context size limit?
| rock_hard wrote:
| It's indeed a challenge
|
| For many applications such as talking to pdfs you can use a
| vectors db like pinecone
|
| But that doesn't work well for schematics because for of the
| interesting use cases you need access to the whole thing.
|
| Here is what's been working for us
|
| 1. Extreme compression and summarization of the data we
| dynamically put in the context 2. Leverage the extreme amount
| of world knowledge the cutting edge models have
| arcticbull wrote:
| Out of curiosity, I noticed in the video that it recommended
| for a voltage regulator either an LM7805 or an LM1117 - either
| a super inefficient 5V regulator that has no business in new
| designs, or a 1.2V low-dropout 800mA regulator that is probably
| not appropriate to the other components it recommended (i.e. an
| LM7805 -> LM1117 would be 36% efficient at best).
|
| It then also recommends a LiPo battery with a nominal 3.7V
| which obviously wouldn't be compatible with its LM7805
| recommendation.
|
| It also recommends an ESP8266 which is a 3.3V part so neither
| of the recommended regulators, nor the battery alone, would be
| appropriate.
|
| Also, it recommends a 168MHz STM ARM micro - but it already has
| an ESP8266 with GPIO.
|
| I'm not sure what it's suggesting I build but it doesn't really
| sound like a working environmental radiation logger ;)
|
| How should I think about this?
| stavros wrote:
| Why is the battery alone not appropriate for the ESP8266? It
| runs just fine off a lithium battery.
| rock_hard wrote:
| In this case it seems to be giving examples of common ICs
| that are voltage regulators - these answers to high level
| questions are pretty vague by default.
|
| We've had good results by asking follow up questions like
| "what power supply IC could I use to power a 3.3v
| microcontroller from a 3.7V nominal LiPo battery over the
| whole battery voltage range?".
|
| I asked that question and I got: LM3940 and AMS1117-3.3 (LDO,
| high drop out but probably ok for low current - one isn't in
| stock but it doesn't have stock info yet), and TPS62203 and
| ADP2108 (bucks, both seem appropriate). These answers should
| get better as Copilot gets access to more and more tools.
| arcticbull wrote:
| btw I hope my comment didn't come across as too negative,
| like many folks I'm still trying to frame my own thinking
| around this kind of tooling. Thanks for the follow-up.
| Applejinx wrote:
| Not at all. I thought it was salient and very much what I
| wanted to know about. It seems there will be a heck of a
| lot of comments saying 'this is so awesome!' and this
| isn't a field where I'm able to look at the answer and
| immediately see the list of howling errors and
| hallucinations, so I'm very glad somebody can.
|
| It's all very well expecting the hallucinations, but
| specificity beats Ludditeism every day. My gut reaction
| was 'ho boy, I'd better not trust this' but I didn't have
| the domain knowledge to understand why the GPT advice was
| dangerous. You did.
| assimpleaspossi wrote:
| I find comments similar to yours about ChatGPT all over the
| internet. I finally took the time to ask that some questions
| over the last few days. All the answers it gave were mundane
| and expected from any click bait web site you can find. I
| Googled the same questions and found similar answers.
|
| Some personal questions it refused to answer or give
| suggestions because "only you can decide" was the response.
|
| I'm very suspicious of all this. I'm thinking the only real
| benefit--some may say--is the chat aspect. You can carry on a
| conversation rather than having to determine a proper Google
| search over and over again.
|
| Which makes me think there is some hype involved.
| gfodor wrote:
| You're probably not using GPT-4, the internet is being
| flooded with takes about GPT-3.5's quality like this simply
| because the author doesn't know there is a meaningful
| difference with the new model.
| jacquesm wrote:
| If GPT-X would just shut up if it doesn't know something
| it would already be 10x more useful than it is right now.
| gedy wrote:
| Isn't that the core issue? Its model doesn't really
| "know" what is real or made up.
| assimpleaspossi wrote:
| When I go here: https://openai.com/product/gpt-4 it says
| "try on chatgpt plus" and sends me to the same page I log
| in with and that's where I've been testing it.
| sbohacek wrote:
| Be sure that you select GPT-4 from the drop down list of
| models. For each new chat, it reverts back to default
| GPT-3.5.
| pigeons wrote:
| GPT-4 still confidently makes up sources for wrong
| answers and throws subtle mistakes (the obvious mistakes
| aren't as big a nuisance) into output.
|
| This isn't to say gpt-4 isn't cool or impressive or a
| development to watch and learn about and be excited
| about, but I frequently see criticism dismissed as "you
| must be using 3.5" while I find 4 still costs more time
| than it would have potentially saved.
| masto wrote:
| Opened site. Chat popped up in the corner and started making
| sound effects. Closed site.
|
| I guess it doesn't matter if a few people are annoyed, if the end
| result of these things is a new increase in conversions. But I
| wish "don't annoy people" was actually in the product
| requirements.
| LesZedCB wrote:
| > Please don't complain about tangential annoyances--e.g.
| article or website formats, name collisions, or back-button
| breakage. They're too common to be interesting.
|
| https://news.ycombinator.com/newsguidelines.html
| spaceman_2020 wrote:
| Ah the trusted HN top comment that's never about the product
| but a complaint about a minor marketing annoyance on the
| website.
| jrockway wrote:
| Most "annoyance blocker" filterlists get these. In this case
| it's intercom.io which I block with Adguard's Annoyances lists:
| https://adguard.com/kb/general/ad-filtering/adguard-filters/
| [deleted]
| satvikpendem wrote:
| I can't imagine using the internet without uBlock Origin,
| SponsorBlock, and a whole host (no pun intended) of filter
| lists.
| aloer wrote:
| The timing could not be more perfect. Yesterday I realized that I
| need to create my very first PCB to repair and smartify a device
| that I broke. Today I thought I should use ChatGPT to better
| understand how things work. And now this.
|
| There are a lot of space constraints so first thing is figuring
| out if it is even possible to build as small as needed. Usually I
| would probably be better off starting to build big first and then
| scale down. But I feel confident that I can already get quite far
| with the amazing resources out there.
|
| I spent hours watching videos about soldering, PCB design, some
| of the components I think I would need (very flat flexible
| cables, small ESP32 SMD, no space for USB) and then how to start
| actually doing the work. My last exposure to electronics was in
| grade 8 and that was very heavy on cables.
|
| This 3h video here was very helpful to understand the process.
| It's an overview of building your own ESP32 dev board with
| EasyEDA from start to finish: https://youtu.be/S_p0YV-JlfU
|
| I like these top-down big picture kind of things that go over
| everything in just enough detail to know what to search for. Does
| something like this but with flux.ai exist for complete
| beginners? The tutorials seem more focused on users switching
| over from other PCB design tools.
|
| Every step of the way I am just amazed how today I can get
| physical things custom made and shipped within days.
|
| And then there's fun videos like this here: Small scale fully
| automated PCB production in what is basically a garage ->
| https://www.youtube.com/watch?v=ZH6ljHUx_IM&t=800s
| jacquesm wrote:
| That last video... drool.
| amelius wrote:
| This phones home, so I cannot use this as per my company's
| regulations.
| fortyseven wrote:
| Why on earth would you call this "copilot" when GitHub has
| already long established that as a name in this space? :I
| paulgb wrote:
| I believe aviators have been using it longer.
| gojomo wrote:
| Indeed, but under trademark law, the context-of-use matters,
| and is what allows generic terms from one domain - like
| 'copilot', 'apple', 'slack', 'y combinator' - to become
| defensible trademarks in another commercial-offerings domain.
|
| From this landing page's headline & 1st paragraph, I was
| still thinking they were talking about the broader-market,
| better-known Github Copilot - also a for-pay LLM-driven
| coding assistant! - in some way. In the 2nd paragraph, I saw
| they were just reusing the name of someone else's LLM coding
| assistant for something different that they independently
| trained.
|
| Note also the current submission headline here is "ChatGPT
| for Hardware Design", not the page's "AI For Hardware Design
| with Copilot".
|
| Did the submitter not use the usually-requested original page
| title, because they knew `Copilot` would be misunderstood?
| (They created another misunderstanding via their change:
| ChatGPT is only an analogy for what Flux.ai's product is
| doing, rather than a contributing part of the system.)
| gowld wrote:
| If they aren't using ChatGPT in Flux.ai, that's textbook
| trademark misuse!
|
| Check out my new product -- It's Windows for Raspberry Pi!
| (Actually a Ubuntu port)
| gojomo wrote:
| Their page doesn't mention 'ChatGPT' - that analogy was
| added by the submitter. But, Flux.ai has named their LLM-
| based coding assistant 'Copilot'.
| Czarcasm wrote:
| Github can't monopolize the word "copilot". It's a basic
| english word to describe someone that is assisting you to steer
| a vessel/team/project. It's been around for hundreds of years
| in naval industry, and in aviation since the dawn of flight.
| gowld wrote:
| Oh they can if they get a trademark. It's a navigational
| term, but not a computing term. Inventing a new meaning for a
| word standard use of trademark.
| iamflimflam1 wrote:
| Was wondering the same thing - just seems a bit daft and is
| going to really confuse people.
| UncleOxidant wrote:
| Yeah, this seems like a lawsuit waiting to happen. Rename it to
| 'Solder' or something before that happens.
| celeritascelery wrote:
| GitHub doesn't own the copilot trademark. I would actually
| like to have these assistants called "copilots" instead of
| "coding LLM". Since these are going to be a part of our lives
| let's use a useful and memorable name.
| gojomo wrote:
| Simply via commercial use, Github could choose to assert a
| common-law trademark on 'Copilot' within their field-of-
| use. But also, they've registered "Github Copilot" at the
| USPTO:
|
| https://trademarks.justia.com/974/60/github-97460083.html
| pulvinar wrote:
| Presumedly they would likewise register "Flux Copilot"?
| mhb wrote:
| I recently used ChatGPT to find a part. Maybe this was an
| anomalous result, but it was wrong. Don't know if this will be an
| issue with your project.
|
| Me: Is there a digital to analog converter with an 8V analog
| range and serial input?
|
| CGPT: Yes, there are several digital-to-analog converters (DACs)
| available with an 8V analog range and serial input. One example
| is the AD5541A DAC from Analog Devices. It has a 16-bit
| resolution and can accept serial input in the form of SPI or QSPI
| signals. The output voltage range is programmable and can be set
| to 0 to 8V using an external reference voltage.
|
| Another example is the MAX5389 DAC from Maxim Integrated. It has
| an 8-bit resolution and can accept serial input in the form of
| I2C signals. The output voltage range is also programmable and
| can be set to 0 to 8V using an external reference voltage.
|
| These are just a couple of examples, but there are many other
| DACs available from different manufacturers that meet your
| specifications.
|
| Me: Those parts are limited to 6v max
|
| CGPT: I apologize for the mistake in my previous response. You
| are correct that the AD5541A and MAX5389 DACs have a maximum
| output voltage range of 5V, and they cannot meet your requirement
| of an 8V analog range.
|
| However, there are other DACs that can meet your specifications.
| For example, the DAC5578 from Texas Instruments is a 16-bit DAC
| that can operate from a single 5V supply and has a programmable
| output range up to 10V. It also supports a serial interface with
| SPI or MICROWIRE protocols.
|
| Another option is the MCP49xx series from Microchip, which
| includes several DACs with output voltage ranges up to 10V and a
| serial interface with SPI or QSPI protocols.
|
| I hope this information is helpful, and please let me know if you
| have any further questions.
| TT-392 wrote:
| Similar experience here, the only thing I have found it to be
| somewhat okay at, is figuring out what would be the somewhat
| "jellybean" version of a component I am looking for. It is
| sometimes kinda difficult to figure that out through the usual
| parametric search. Though, even then, it has recommended me
| components that are very much not what I asked for, stuff as
| simple as recommending me an npn instead of a pnp.
| pulvinar wrote:
| Interesting. I tried the same question (each a new
| conversation, GPT4) and 10V and above it catches, but 8V seems
| to be in its blind spot. Maybe it hasn't learned anywhere to
| take absolute maximum ratings seriously?
| pulvinar wrote:
| Update: after asking it to explain absolute maximum ratings
| and check that for this part (which it knew correctly) and
| pointing out its error, it finally suggests a reasonable
| part, the AD5758.
|
| It's clearly missing experience with magic smoke.
| numpad0 wrote:
| ChatGPT talks all from its memory, they're not suitable for
| hard data. Bing Chat type of architecture is more suited,
| though it still couldn't find a part matching that criteria.
| steve_adams_86 wrote:
| I've had this experience as well. I find the trick is the
| provide as much information as possible and keep the expected
| solution's scope to a minimum. That flux is including context
| about the project a user's working on will probably help more
| and more as the project is built out, which is cool. The second
| part though, keeping query scopes narrow, is up to the user I
| guess.
|
| It would be interesting if circuit simulation could be used to
| vet out suggestions, but you'd need a vast database of
| components and their pinouts, GPT or something else would need
| to know how to arrange the circuit in order to simulate them
| properly, and so on. That's the only way I can think to
| validate outputs at the moment, though.
| CamperBob2 wrote:
| Same here, when asking for an N-channel complement for a
| P-channel power FET. It would get some of the parameters right,
| such as dissipation and package type, but would get others
| wrong, like insisting on 800V Vds parts when the original
| target was a 50-volt part.
|
| Promising, but not quite ready for prime time yet.
| hammyhavoc wrote:
| Can report similar experiences.
|
| Just signed up for a free account, will give it a try, but
| expecting hallucination to be a major issue.
| gowld wrote:
| This report is unhelpful without the GPT version you are using.
| amelius wrote:
| What I want most is simulation models of commercial components,
| and a good simulator...
|
| Oh and something that can read datasheets for me, and extract
| important parameters (or convert them to spice models).
|
| A tool that can hunt for cheap components would also be nice.
|
| Apart from that, I don't think I like to have any fuzziness in my
| workflow.
| rock_hard wrote:
| Yes, us too!
|
| We are working on all of this right now and have a bunch more
| announcements over the coming weeks and months.
|
| Stay tuned!
| phendrenad2 wrote:
| Flux is cool, but I don't know who the customer is. I feel like,
| as a hobbyist maker, I might be it and just don't know it?
| rock_hard wrote:
| Founder here:
|
| Incredibly stoked to announce this today!
|
| This is a dream a long time in the making. When we first thought
| of rebuilding the hardware design tooling stack from scratch, AI
| driven design seemed like the dream at the end of the
| tunnel...only 3+ years later we are here
|
| Given the open ended nature of AI Expert agents we are launching
| a community preview. We are committed to keep building
| http://flux.ai in the open and are excited to discover this new
| realm with all of you.
|
| Hit me with questions
| nunuvit wrote:
| Have you reevaluated the decision not to implement much by way
| of basic interface features like symbol and footprint editors
| for such a long time? It's a real barrier to even playing
| around with the software. I want to see you succeed, and my
| experience in the EDA industry and as an electrical engineer is
| making me wonder about that approach.
|
| It makes sense if you're just shopping it around to the EDA
| incumbents since they'd have you redesign those parts anyway,
| but the fact that you currently offer a paid subscription to
| users makes me think that either you've underestimated or I've
| overestimated the importance of having those features by now. I
| guess that could also make sense if you want a more manageable
| user base for now.
| rock_hard wrote:
| Not sure I follow...maybe there is a misunderstanding here
|
| We do have symbol and footprint creation and editing
| capabilities...in fact the vast majority of parts on the
| platform have been created by users.
|
| Now what we don't do is offer a modal editor like legacy
| tools do...instead it happens all in the same mode, which
| simplifies a lot of the UX and also provides powerful new
| abilities such using a schematic to create simulation models.
|
| Now that said I think we can do a lot more here to further
| improve the experience and we def will but you are right in
| that it hasn't been much of an issue which is because you
| have access to a vast preexisting library in the platform
| nunuvit wrote:
| The last time I tried to evaluate it was a long time ago
| and it seemed to be all svg uploads. I had to re-read the
| docs more closely after reading your comment. It says you
| need to enter svg only for non-rectangular symbols, but
| it's not clear if you can create or modify a pad shape
| other than circular or rectangular from within the tool.
| Obviously good progress, and more than I understood when I
| wrote my previous comment. That's minimum viable for many
| to start using it, so my concerns are addressed.
|
| The single mode thing is cool.
| steve_adams_86 wrote:
| If this works well, are you interested in training a model
| specifically around the domain you work in so you could get
| deeper integration with your product?
|
| I have a personal project similar in concept to flux, but
| rather than working at the circuit level, it's at the device,
| firmware, and infrastructure level. I've been trying to use GPT
| to intuit how to network devices using different protocols,
| such that it might be easier for lab techs (for example) to
| discover how to manage and maintain their experiment tooling
| and infrastructure. It's really hard, though. The outputs and
| level of integration are mind-bendingly good, but... It's not
| perfect, which makes it too clumsy or even dangerous for what I
| want to build.
|
| I think I envision something like GPT transforming human
| language into prompts for a narrower model with more
| predictable outputs, which is far more aware and capable with
| the application's logic and data. The user experience could
| then give you the conversational ease, yet far better
| application integration as well.
|
| Anyway, just curious what you're thinking and very excited
| about projects like this. This is really cool.
| rock_hard wrote:
| Yea def looking into this
|
| We already use a multi model approach and mix of non
| deterministic and deterministic tooling in the pipeline to
| optimize for a given task
|
| Lots of more work to be done here
| heyzk wrote:
| The flux docs indicate that you're using a custom-trained
| LLM and in another comment it was mentioned you're using
| LangChain (to integrate non-deterministic tooling perhaps).
| Just curious, but are you using some combination of your
| own model, GPT3/4, and calculators / datasheet readers /
| etc?
| rock_hard wrote:
| The answer is: all of it!
|
| Not everything is in prod yet but we def combine all the
| things you can imagine to pull this off
| causi wrote:
| GPT is really bad at math. Doesn't that mean it's also bad at
| doing the math for designing circuits?
| steve_adams_86 wrote:
| Maybe not. It understands data sheets, and seems to be able
| to connect the dots based on probabilities around connecting
| components together. If you don't ask it to do large-scale
| design tasks, it's okay at narrowly scoped tasks like this.
|
| If it's wrong, you can determine that during simulation. You
| could also assert that in the background, I suppose -- prune
| the bunk suggestions by the language model before presenting
| them.
|
| In my own experiments I find GPT can succeed in complex tasks
| if you prompt it multiple times at different steps of the
| task, and have some level of recursive validation and re-
| prompting to keep it in line. In a case like this I have a
| feeling it would do a great job, and would be especially
| useful for the discovery/exploration phase of a new project.
| xyzzy123 wrote:
| Have you tried recently? I am getting surprisingly good
| results lately with GPT-4 on basic physics problems with no
| prompt engineering (just stating the problem). It seems to
| recognize when it needs to "think step by step" and just do
| it.
| hammyhavoc wrote:
| Here's another interesting idea: the marketing blurb mentions
| reducing costly errors--but with the amount ChatGPT
| hallucinates, how does this work? What steps have been taken
| to mitigate hallucination?
| rock_hard wrote:
| LLMs do indeed hallucinate.
|
| What's been working well for us is to give it access to
| factual data sources such as calculators, component data
| sheets, etc.
|
| It does really well from our tests in the past few weeks,
| so well that we decided to invite everyone to explore the
| boundaries with a community preview
|
| Just give it a shot and report back
| hammyhavoc wrote:
| Can you elaborate on "really well"? Because a few weeks
| of testing and "really well" versus the claim of reducing
| costly mistakes on the marketing blurb whilst
| simultaneously acknowledging hallucination doesn't
| inspire confidence.
|
| I'd be interested to know a lot more about testing
| methodology too. A hallucination could be a much more
| expensive problem than someone simply making a basic
| mistake that someone might otherwise catch if they were
| doing things the usual way.
|
| Not trying to be obstinate, genuinely interested, but
| sceptical as my experience of ChatGPT has been very
| negative due to hallucinations, to the point that I find
| that the marketing materials sound far too good to be
| true versus the comment here, which seems much more
| grounded.
| rock_hard wrote:
| Please def report back if you encounter it to hallucinate
|
| This is exactly why we are doing the community
| preview...to make it your favorite design tool.
| rock_hard wrote:
| To give you an example of the typical response quality we
| encountered:
|
| @copilot can you design a low pass filter for me with 3db
| point of 300khz?
|
| copilot: Sure, I can help you design a low-pass filter
| with a 3dB point of 300 kHz. A simple passive RC
| (resistor-capacitor) low-pass filter can be used for this
| purpose. To calculate the values of the resistor (R) and
| capacitor (C), you can use the following formula:
|
| f_c = 1 / (2 pi R * C)
|
| Where f_c is the 3dB cutoff frequency (300 kHz), R is the
| resistor value, and C is the capacitor value. Let's
| choose a standard resistor value, for example, 1 kO.
| Then, you can calculate the capacitor value as follows:
|
| C = 1 / (2 pi R f_c) = 1 / (2 pi 1000 300000) [?] 530.5
| pF
|
| Since 530.5 pF is not a standard capacitor value, you can
| use the closest standard value, which is 560 pF. With
| these values, the actual 3dB cutoff frequency will be
| approximately:
|
| f_c = 1 / (2 pi 1000 * 560e-12) [?] 283.5 kHz
|
| The low-pass filter can be assembled by connecting the 1
| kO resistor in series with the input signal, followed by
| the 560 pF capacitor connected to the ground. The
| filtered output can be taken across the capacitor. This
| design will give you a first-order RC low-pass filter
| with an actual 3dB point of approximately 283.5 kHz.
| hammyhavoc wrote:
| And how about the negative responses involving
| hallucination? Ideally giving an example of the worst
| hallucination encountered thus far and least worst thus
| far.
|
| As a potential customer, I'm more interested in knowing
| where the potential known failure points or points of
| friction are than knowing what's working well.
|
| Yes, when it works, it's certainly compelling in its
| responses--but as it never knows when it is wrong, it is
| equally compelling at a cursory glance when it
| hallucinates.
|
| For most folks interested in this, their Dunning-Kruger
| complex will prevent them from picking up on when it's
| wrong because it's so convincing and sure of itself.
| rock_hard wrote:
| I hope it would not lol
|
| For starters: From our testing it's really extremely good at
| providing the right formulas to solve the problem at hand.
|
| But you are right, these models are inheritely non
| deterministic and therefore can struggle with things like
| math. The solution is to provide it access to tools such as a
| calculator which works really well.
| gowld wrote:
| > rebuilding the hardware design tooling stack from scratch
|
| This kind of talk is tacky and repels technical users.
| zlstone1992 wrote:
| This is absolutely been a long-wait implementation of GPT.
|
| What is the process of adding component to the list? Additional,
| could rule to been user defined (to minimum EMI/EMC, e.g.)?
| rock_hard wrote:
| Yeah you can create your own components or work with the over
| 250k we have in the public library.
|
| Flux is designed much like GitHub in this regard...you can fork
| other people projects and what not.
|
| You can already ask it today to perform EMI/EMC checks for
| you...and we have started thinking about using it to write
| static rules for you among other things
| lloydatkinson wrote:
| It's AI said it added components to the schematic but there is
| nothing there?
| lnsru wrote:
| Nice stuff. But hard to find good application in my environment
| for it. I mostly re-work old designs or use reference designs
| with particular chips (that the company has in stock at the
| moment). Maybe somebody could greatly benefit without the
| limitations I have at work.
___________________________________________________________________
(page generated 2023-04-27 23:00 UTC)