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

21–30 of 165 posts

Re: ChatGPT for Hardware Design

#21

Post by xyzzy123 »

causi wrote: post #3
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…

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

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.

Re: ChatGPT for Hardware Design

#22

Post by steve_adams_86 »

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…

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.

Re: ChatGPT for Hardware Design

#24

Post by rock_hard »

steve_adams_86 wrote: post #17
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…

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

Re: ChatGPT for Hardware Design

#25

Post by rock_hard »

zlstone1992 wrote: post #23

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.)?

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

Re: ChatGPT for Hardware Design

#27

Post by pulvinar »

pulvinar wrote: post #18
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?

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.

Re: ChatGPT for Hardware Design

#29

Post by CamperBob2 »

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…

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.

Post reply on HN