[rock_hard]

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

[steve_adams_86]

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]

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]

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]

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

[nunuvit]

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]

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]

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.

[rock_hard]

Thanks for giving us another shot

The circular and rectangular options have a bunch of transformations available…you can make turn circles into oblong shapes simple by providing async size value and you can set a corner radius for rectangular pads and even your layout.

And as you probably saw you can load symbols as svg and you can also load custom pad, layout and silk shapes either as svg or dxf

Less known but also works for shapes that you are reading off datasheets is that you can also just type in a svg path into the shape field of each object type

How philosophy is to make the most common things really simple and straightforward and the edge cases possible. But yeah, someday we’ll also ship online shape editing features

[nunuvit]

In that case, the docs don't really do justice to it. They still read as if many features don't exist yet.

[causi]

GPT is really bad at math. Doesn't that mean it's also bad at doing the math for designing circuits?

[steve_adams_86]

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.

[hammyhavoc]

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]

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]

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]

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 kΩ. 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 kΩ 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]

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]

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.

[xyzzy123]

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.

[rock_hard]

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.

[jareklupinski]

when I'm building circuits, usually I know what I want to design on a high level, but once it comes time to turn the schematic into a BOM, I get bogged down in minute differences between similar components

e.g. most recently, I needed a boost converter with at least 300mA sustained I at 3.3V coming from the lowest V source possible (alkaline battery powered gadget) After an hour or so of searching I had to choose between TLV61220 and TPS61021A . Maybe there is a better third chip? At this point I ran out of time to research and just figured this the TPS61021A would do.

Digikey/Mouser/etc have parametric filtering (when it works), but optimization among three variables is not the strong suit there, especially when you have, say, an 8mm square to fill and cost is a factor (and availability/flexibility between footprints)

I would love to use this as a fair recommendation engine (that isn't sponsored by TI, skewing all results towards their products) where I can give it my circuit's minimum/recommended/maximum parameters and have it suggest applicable parts, or even take my finished designs and suggest cheaper alternatives for parts that match the design's footprints but have lower capabilities, if that's all my circuit needed in the first place.

(just threw my query into chatgpt and it suggested https://www.ti.com/product/TPS61221) not bad.

[newswasboring]

I would love to hear/read about your journey. Especially what your thoughts were at the start. There wasn't much like ChatGPT when you started 3 years ago, wasn't that fog scary af? How many times did you pivot/change your AI models?

[rock_hard]

We knew that we had to build a foundation first to have any shot at getting AI right.

I worked at Meta for years and knew first hand that ML/AI can only ever get good with loooots of training data.

So we needed a way to produce lots of high quality training data first and a way for users to be able to reason about results and edit them.

There is a graveyard of failed AI hardware design projects and one thing they all have in common is that they are black boxes…its very obviously the wrong approach. But every week a new one pops up…I don’t even understand why anyone funds this stuff anymore frankly…it can’t work.

So we embarked on building our own eCAD editor first…that was gonna be step number one. It was also the hardest and most expensive way to go about it… but if you have big dreams then you just have to go and do big things. I recent these get rich quick schemes personally anyways…I love doing hard things!

LLMs just starting to get good around the time we had the editor ready for public launch (after years of beta) was a happy coincidence that makes us look like geniuses now. But I take it lol.

We had been actively playing on the side for the past 6 months on ideas for first AI features as we geared up for launch of the core editor but the critical insight to use our existing projects comments surface was a last minute brain fart that came to us about 6 weeks ago.

Things went pretty quick from there and we are moving extremely fast now that we have the right foundation.

Excited times!

[gowld]

> rebuilding the hardware design tooling stack from scratch

This kind of talk is tacky and repels technical users.