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

111–120 of 165 posts

Re: ChatGPT for Hardware Design

#111

Post by newswasboring »

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?...

None of you are. You are using the tool improperly. The tool cannot spit out entire applications yet, especially if all you told it was the final outcome. I see GPT-4 as a junior programmer in my team who is unusually productive. It cannot do the design for me, but executing it is a piece of cake for it.

Re: ChatGPT for Hardware Design

#112

Post by ugh123 »

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…

Do you do any fine tuning of the model for circuit analysis and other hardware design literature?

Re: ChatGPT for Hardware Design

#113

Post by drones »

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 be reminded that people are actually trying to make useful products in a world where it seems everyone is trying to sell you a solution with no problem.

Re: ChatGPT for Hardware Design

#114

Post by 1letterunixname »

x86x87 wrote: post #99
1letterunixname wrote: post #98

We are witnessing the arrival of the technological singularity in slow motion. It is becoming possible for AI systems to rapidly design hardware and software systems from the requirements of individuals who do not necessarily understand the subject matter. I give tech 10 years before most of it is accomplished by AI and most people in tech will be forced out. Like DC elevators, some will remain, but not like it was.

i give AI at least another 500 years until the I in AI actually stands for intelligence. See what I did there? Everyone can make outrageous claims without backing them up whatsoever :)

Nope. You added nothing of value. You can be a fool and deny numerous forms of narrow AI while AGI is a flying car distraction that doesn't matter. It is your error conflating the two.

Re: ChatGPT for Hardware Design

#115

Post by digitcatphd »

Excellent product! I’m curious how you are communicating data from the project and handling memory to ChatGPT, have you found it handles new external data well without first modifying its format or structure or have you had any memory issues?

Re: ChatGPT for Hardware Design

#116

Post by robertfall »

outworlder wrote: post #87
assimpleaspossi wrote: post #46

Earlier quoted context omitted.

I find comments similar to yours about ChatGPT all over the internet. I finally took the time to ask that some questions over the last few days. All the answers it gave were mundane and expected from any click bait web site you can find. I Googled the same questions and found similar answers. Some personal questions it refused to answer or give suggestions because "only you can decide" was the response. I'm very susp…

> Which makes me think there is some hype involved. There's _a lot_ of hype. It's a good tool if you forget about any "intelligence" and just think of it as a tool. We don't expect search engines to be 'intelligent', we expect them to return results we are interested in, in an efficient manner. In the case of this and similar tools, it is a text generator. It will generate _something_ based on your input. In many cas…

GPT 4 is a massive improvement in this regard.

Copilot specifically asked me to provide the capacitance value for the capacitor closest to the comment pin in response to my question about optimal resistance for a resistor. Once I provided the value (by setting it in the tool, not by typing it in the chat) and asked it to try again it thanked me for the new info and gave back a good resistance value and how it arrived at it.

Re: ChatGPT for Hardware Design

#117

Post by gfodor »

pigeons wrote: post #64
gfodor wrote: post #58

Earlier quoted context omitted.

You’re probably not using GPT-4, the internet is being flooded with takes about GPT-3.5’s quality like this simply because the author doesn’t know there is a meaningful difference with the new model.

GPT-4 still confidently makes up sources for wrong answers and throws subtle mistakes (the obvious mistakes aren't as big a nuisance) into output. This isn't to say gpt-4 isn't cool or impressive or a development to watch and learn about and be excited about, but I frequently see criticism dismissed as "you must be using 3.5" while I find 4 still costs more time than it would have potentially saved.

Of course this is possible but usually criticizing a dismissal like this as being wrong comes after it has been proven wrong.

Re: ChatGPT for Hardware Design

#118

Post by pulvinar »

gojomo wrote: post #100
pulvinar wrote: post #75

Earlier quoted context omitted.

Presumedly they would likewise register "Flux Copilot"?

Do you think I could offer a custom-built Windows PC under the registered trademark "Gordon's Macintosh"?

Except that "copilot" doesn't appear to be registered by itself in this field, only in combinations. But we'll see.

Re: ChatGPT for Hardware Design

#119

Post by rock_hard »

arcticbull wrote: post #61
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…

btw I hope my comment didn't come across as too negative, like many folks I'm still trying to frame my own thinking around this kind of tooling. Thanks for the follow-up.

We are all good

Re: ChatGPT for Hardware Design

#120

Post by arcticbull »

rock_hard wrote: post #119
arcticbull wrote: post #61

Earlier quoted context omitted.

btw I hope my comment didn't come across as too negative, like many folks I'm still trying to frame my own thinking around this kind of tooling. Thanks for the follow-up.

We are all good

I look forward to following your work. I don't know what the ideal integration of generative AI and hardware design is, but I do feel like there are opportunities. Excited to see what y'all cook up.
Post reply on HN