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

121–130 of 165 posts

Re: ChatGPT for Hardware Design

#121

Post by rock_hard »

drones wrote: post #113

As someone who is not well versed in the current LLM paradigm, how are the LLMs for technical domains trained? I can imagine how a model based off interent text would make for a _general_ conversational partner, but I'm unsure how a model would produce accurate information from such a niche prompt. Also curious: has anyone created an LLM for circuit schematics trained on HDL code? Very cool application. It's nice to…

For starters you can feed it every book on electronics and every datasheet out there

That plus broad world knowledge and reasoning abilities gets you very far

And then you dynamically provide proper context and prompting as well as deterministic tooling such as a calculator to and voila…you got your new favorite virtual team mate :)

Re: ChatGPT for Hardware Design

#122

Post by newswasboring »

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…

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?

Re: ChatGPT for Hardware Design

#123

Post by exmadscientist »

Senior EE here! I'm not at all impressed with this page because you don't show the tool doing anything interesting. All your examples are undergrad-course or lower level of difficulty. I feel like reading several of the tool's responses actually wasted my time because it took longer for me to read the text than to come up with a better answer. (Though admittedly I've been at this a while. And the check-if-I-screwed-up-the-chip-select one was pretty neat, I did like that!)

Can you demo something with a little more bite to it? Seeing that you can help me save time on actually-meaty pieces of design work would make a lot of difference for me. Maybe something like "design a correctly biased class-AB output stage, with rail-to-rail swing on +/-5V rails, intended for use boosting op-amp output current"? That is an interesting one because (1) it's a small but real, useful, meaty problem with (2) a lot of examples out there in the world to copy from with (3) a nontrivial added constraint in rail-to-rail out but (4) even solutions that aren't all the way there are useful.

Re: ChatGPT for Hardware Design

#124

Post by kramerger »

exmadscientist wrote: post #123

Senior EE here! I'm not at all impressed with this page because you don't show the tool doing anything interesting. All your examples are undergrad-course or lower level of difficulty. I feel like reading several of the tool's responses actually wasted my time because it took longer for me to read the text than to come up with a better answer. (Though admittedly I've been at this a while. And the check-if-I-screwed-u…

Not a senior EE, but equally unimpressed.

The thing about LLM is that it answers based on data it has seen before. So if enough posts on stackoverflow in 2021 claimed mps340 is the best CPU for beginners, that's what the AI will recommend.

There are 3 problems with this: it can and will be gamed, it is usually more conservative and not on the bleeding edge, and finally you can't ask questions you did't know you needed to ask so feature products built by random dude using chatgpt will have reliablity and safety issues.

Re: ChatGPT for Hardware Design

#125

Post by SanderNL »

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?...

The largest models like GPT4 have the interesting property to really, really finish what you started. If you start with flaws of any kind, it will continue to produce them. The inverse is true as well.

This is an actual thing[1] and it’s something larger models are actually worse (better?) at. They score higher and higher on the loss function (did I predict correctly), but their utility (does it work) goes down.

Just thought it was noteworthy.

[1] https://arxiv.org/abs/2102.03896

Re: ChatGPT for Hardware Design

#126

Post by phendrenad2 »

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.

Same with login with Google

Re: ChatGPT for Hardware Design

#127

Post by neodypsis »

I wanted to give it a try, so I went to sign-up with Github but the process failed. So then I signed-out of Github and tried to login again but Flux loaded someone else's profile! Had to de-authorize Flux from my Github.

Re: ChatGPT for Hardware Design

#128

Post by neodypsis »

gfodor wrote: post #57
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’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.

Have you tried KiCad? There are some interesting courses on Udemy about using it for PCB design.

Re: ChatGPT for Hardware Design

#129

Post by neodypsis »

gabereiser wrote: post #88
markwu2001 wrote: post #60

Earlier quoted context omitted.

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 th…

This is what's been holding me back from PCB design. Like, I know the math, but there's forces at play beyond just V1/R1=V2 kinda stuff. I'm really keen to see if an LLM can assist a hobbyist in making sound, quality, designs that aren't going to break his/her wallet when the sheet comes in and none of it works. About 12 years ago I designed an RF addon board for an RC car (to toggle lights). Even something as simple…

This XSeries on edX [0] looks promising for some of the prerequisite knowledge. Then for PCB design specifically, there are specialty courses on Udemy, for example, "KiCad Like a Pro" [1].

[0] https://www.edx.org/xseries/mitx-circuits-and-electronics

[1] https://www.udemy.com/course/kicad-like-a-pro-3e/

Re: ChatGPT for Hardware Design

#130

Post by robertfall »

neodypsis wrote: post #127

I wanted to give it a try, so I went to sign-up with Github but the process failed. So then I signed-out of Github and tried to login again but Flux loaded someone else's profile! Had to de-authorize Flux from my Github.

Hi,

I'm on call for the team this week.

We'd love to get more information here as we take anything around privacy and authentication very seriously. I'd like to get usernames of profiles involved and rule out being redirected back to a page you were visiting before signing in.

Would you be open to discussing further? You can reach me at robert.herbst@flux.ai. Being able to discuss with you directly would be really helpful.

Alternatively we actively monitor and respond to bug reports filed here: https://feedback.flux.ai/bugreports

Post reply on HN