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

ChatGPT for Hardware Design

docs.flux.ai

Post reply on HN
Print view View original

11–20 of 165 posts

Re: ChatGPT for Hardware Design

#11

Post by markwu2001 »

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.

Re: ChatGPT for Hardware Design

#12

Post by hammyhavoc »

rock_hard wrote: post #10
hammyhavoc wrote: post #6

Earlier quoted context omitted.

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?

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

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.

Re: ChatGPT for Hardware Design

#14

Post by rock_hard »

joshuanapoli wrote: post #7
greg wrote: post #4

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 nee…

How do you deal with designs whose netlist or part list exceeds the context size limit?

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

Re: ChatGPT for Hardware Design

#16

Post by hammyhavoc »

mhb wrote: post #5

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 r…

Can report similar experiences.

Just signed up for a free account, will give it a try, but expecting hallucination to be a major issue.

Re: ChatGPT for Hardware Design

#17

Post by steve_adams_86 »

rock_hard wrote: post #2

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 t…

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.

Re: ChatGPT for Hardware Design

#18

Post by pulvinar »

mhb wrote: post #5

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 r…

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?

Re: ChatGPT for Hardware Design

#19

Post by rock_hard »

hammyhavoc wrote: post #12
rock_hard wrote: post #10

Earlier quoted context omitted.

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

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 othe…

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.

Re: ChatGPT for Hardware Design

#20

Post by celeritascelery »

UncleOxidant wrote: post #15
fortyseven wrote: post #13

Why on earth would you call this "copilot" when GitHub has already long established that as a name in this space? :I

Yeah, this seems like a lawsuit waiting to happen. Rename it to 'Solder' or something before that happens.

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.
Post reply on HN