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

101–110 of 165 posts

Re: ChatGPT for Hardware Design

#101

Post by ZephyrBlu »

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…

I'm curious if you fine-tuned a GPT model with specific hardware-related examples. Based on the OpenAI docs it seems like a pain to get enough good prompt:response pairs for fine-tuning (A few hundred minimum).

Re: ChatGPT for Hardware Design

#102

Post by nunuvit »

hammyhavoc wrote: post #35
rock_hard wrote: post #31

Earlier quoted context omitted.

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 =…

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…

AI is useful for making suggestions, but you shouldn't blindly trust it like that no matter how advanced it gets. It helps you work faster, not beyond your abilities.

Re: ChatGPT for Hardware Design

#103

Post by greg »

leokeba wrote: post #93

Github auth seems broken for me on chrome mac, anyone else ? Here's the error on the login page : You are already signed in, please try signing out and signing in again, or contact us for help. Sometimes I get sent to a profile page, but trying to create a project sends me back to the login page.

Thanks for the report. I’ll look into it tomorrow.

Re: ChatGPT for Hardware Design

#104

Post by ngngngng »

LesZedCB wrote: post #66
masto wrote: post #41

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.

> 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

Just flag the comment

Re: ChatGPT for Hardware Design

#105

Post by rock_hard »

nunuvit wrote: post #59
rock_hard wrote: post #51

Earlier quoted context omitted.

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 simu…

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 co…

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

Re: ChatGPT for Hardware Design

#106

Post by rock_hard »

jrexilius wrote: post #90
rock_hard wrote: post #52

Earlier quoted context omitted.

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 d…

My god.. if you gave it real time stock updates to adjust BoM answers to availability that would be amazing!

Brace for impact!

We have a bunch of features that didn’t make the cut for todays launch but should be available shortly

Re: ChatGPT for Hardware Design

#107

Post by rock_hard »

negative_zero wrote: post #96

I don't mean to sound like a real downer: but I don't see this tool "getting good" for the simple reason of: what are you training it with? I thought ML needs huge datasets? This is great for GitHub's Copilot as there is plenty of high quality, production , open source code they've used without authorisation from the creators (and possibly proprietary code). But this dataset just doesn't exist for hardware developmen…

I think you should give it a shot and see for yourself

This is a first step today, it’s neither done nor perfect…but it kept blowing our and our our most senior testers minds and so we decided to not withhold this incredible technology and rather invite to open experimentation and learning.

Re: ChatGPT for Hardware Design

#108

Post by rock_hard »

phendrenad2 wrote: post #36

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?

Our Mission is to take the "hard" out of hardware so anyone, from makers to businesses, can easily turn ideas into products.

So def give it a shot!

Re: ChatGPT for Hardware Design

#109

Post by MuffinFlavored »

boringuser2 wrote: post #95
markwu2001 wrote: post #11

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 c…

I have no idea what you're talking about, but my experience 100% mirrors yours in most cases as a programmer. GPT-4 produces a lot of my code now. I'm leap-frogging my team a bit in productivity because they still don't like it, but it's so close to being undeniable.

I don't get this. I asked GPT-4 to help me build a machine learning program for historical stock prices. It spat back about 8 errors, functions that don't exist, nothing compiled, multiple logic flaws...

Which one of us is lying?...

Re: ChatGPT for Hardware Design

#110

Post by ugh123 »

MuffinFlavored wrote: post #109
boringuser2 wrote: post #95

Earlier quoted context omitted.

I have no idea what you're talking about, but my experience 100% mirrors yours in most cases as a programmer. GPT-4 produces a lot of my code now. I'm leap-frogging my team a bit in productivity because they still don't like it, but it's so close to being undeniable.

I don't get this. I asked GPT-4 to help me build a machine learning program for historical stock prices. It spat back about 8 errors, functions that don't exist, nothing compiled, multiple logic flaws... Which one of us is lying?...

Probably neither of you? I've had better luck coding with ChatGPT when I ask it very concise questions, mainly at the function or small class level, but still asking for enough functionality to feel satisfied. It helps to give it a "shell" of some code, or a starting point of code to build from. I also make sure to ask it not to include 3rd party libraries (I'd consider those under separate discussions with it). It's truly helpful. And that's saying nothing about copilot integration in the IDE which is sooo good.
Post reply on HN