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

141–150 of 165 posts

Re: ChatGPT for Hardware Design

#141

Post by exmadscientist »

spacebanana7 wrote: post #139
kramerger wrote: post #124

Earlier quoted context omitted.

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 neede…

> The thing about LLM is that it answers based on data it has seen before. Modern LLMs are able to perform web searches to make decisions on contemporary data. Once they have proper API support your concerns should be resolved, hopefully in a few weeks. > reliablity and safety issues. The solution to this is fine tuning / RHLF. OpenAI have done a pretty extensive job at getting political safety for ChatGPT with RHLF.…

"RHLF" is Reinforcement Learning from Human Feedback? (Strange acronym.)

I don't see how that helps a a tool become useful to a very skilled person, if the "human" side of things is polluted by 95+% of users having very low skill. It's great that you can train LLMs on the world's best reference material! But I don't see how you can get the world's best updates into that training set without hiring the world's best experts. So the tool will have very little value for anyone above a certain skill ceiling. Search has already fallen victim to this effect (I'm tired of results pages full of beginner material when I have a deeper question!) and I cannot see this being better for augmentation training sets for LLMs.

Re: ChatGPT for Hardware Design

#142

Post by spacebanana7 »

exmadscientist wrote: post #141
spacebanana7 wrote: post #139

Earlier quoted context omitted.

> The thing about LLM is that it answers based on data it has seen before. Modern LLMs are able to perform web searches to make decisions on contemporary data. Once they have proper API support your concerns should be resolved, hopefully in a few weeks. > reliablity and safety issues. The solution to this is fine tuning / RHLF. OpenAI have done a pretty extensive job at getting political safety for ChatGPT with RHLF.…

"RHLF" is Reinforcement Learning from Human Feedback? (Strange acronym.) I don't see how that helps a a tool become useful to a very skilled person, if the "human" side of things is polluted by 95+% of users having very low skill. It's great that you can train LLMs on the world's best reference material! But I don't see how you can get the world's best updates into that training set without hiring the world's best ex…

It should be RLHF, my bad with the spelling.

> So the tool will have very little value for anyone above a certain skill ceiling.

LLMs aren't great for doing tasks you don't know how to do, because you'll eventually have to debug the output. However they excel at performing time consuming tasks that you could do if you really wanted.

That's why I think they'll actually be more useful for experts.

Re: ChatGPT for Hardware Design

#143

Post by hammyhavoc »

nunuvit wrote: post #102
hammyhavoc wrote: post #35

Earlier quoted context omitted.

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.

That's the thing, I'm not actually sure it does help someone work faster if everything it suggests needs to be fact-checked whilst under the guise of being always confident and never knowing it is wrong.

A lot of people liken AI to having a junior role working with you, but most junior positions have been to university and have a pretty solid understanding of a field in the first place. I wouldn't have a junior role hallucinating things that don't exist on a regular basis.

The speed of generating an output is only as meaningful as how consistently correct and appropriate that output is in terms of its value. I remain unconvinced.

Re: ChatGPT for Hardware Design

#144

Post by boringuser2 »

bombolo wrote: post #134
MuffinFlavored wrote: post #109

Earlier quoted context omitted.

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?...

Maybe he just writes really really really simple code all day and faked his way into a developer position? And then his team mates have to fix/redo anything he does? I've seen it happen several times.

Wrong.

Re: ChatGPT for Hardware Design

#145

Post by nunuvit »

hammyhavoc wrote: post #143
nunuvit wrote: post #102

Earlier quoted context omitted.

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.

That's the thing, I'm not actually sure it does help someone work faster if everything it suggests needs to be fact-checked whilst under the guise of being always confident and never knowing it is wrong. A lot of people liken AI to having a junior role working with you, but most junior positions have been to university and have a pretty solid understanding of a field in the first place. I wouldn't have a junior role…

If you don't do your job because you blindly accepted advice from a confident AI, a confident senior engineer, or a confident application note, then you might not have that job for much longer.

I don't know if it will make you personally work faster or not, that's your business to sort out.

Re: ChatGPT for Hardware Design

#146

Post by boringuser2 »

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?...

Asking GPT-4 to make you an entire application as a complete amateur is absurd and shows you don't understand the context window.

Re: ChatGPT for Hardware Design

#147

Post by MuffinFlavored »

newswasboring wrote: post #111
MuffinFlavored wrote: post #109

Earlier quoted context omitted.

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.

> The tool cannot spit out entire applications yet,

Yesterday I had a ticket at my job to extend some functionality in a code base that was probably 200 files and 100+ lines of code in each file, and that's before any `import` references to other libraries.

How can you feed all of these tokens to GPT-4 in a cost effective way so that it knows about your application well enough to recommend/pull off code completion at a human-like level?

Re: ChatGPT for Hardware Design

#148

Post by MuffinFlavored »

SanderNL wrote: post #125
MuffinFlavored wrote: post #109

Earlier quoted context omitted.

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…

> If you start with flaws of any kind

I asked it to start and it provided me the flaws :D I can share the prompt if you'd like.

Re: ChatGPT for Hardware Design

#149

Post by anthlax »

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’ve been unable to replicate this. Could you please show me an example? I ask everyone who makes this claim and have yet to see a concrete example. I just can’t get it to do anything useful for me. I feel like I’m missing the boat!

Re: ChatGPT for Hardware Design

#150

Post by rideontime »

spaceman_2020 wrote: post #73
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.

Ah the trusted HN top comment that’s never about the product but a complaint about a minor marketing annoyance on the website.

Still wondering about your friends' MegaCryptoPolis investments
Post reply on HN