Testing Generative AI for Circuit Board Design • Hacker News Board

Re: Testing Generative AI for Circuit Board Design

#161

Post by exe34 » Sat, Jun 22, 2024, 10:59 AM UTC

surfingdino wrote: post #155

exe34 wrote: post #65

Earlier quoted context omitted.

how long does it take for a child to start doing surgery? publishing novel theorems? how long has the humble transformer been around?

Nobody is telling an experienced heart surgeon to step aside and let a child plan an open heart surgery. And yet, AI and LLMs in particular are being sold as the tools that can do complex tasks like that. But let's leave complex tasks and have a look at marketing behind one of the tools that's aimed at business. The messaging of one of the ads I'm seeing promises that the tools in question can summarise a 150-page lo…

we do get consultants coming into companies and telling the experienced professionals how to screw up stuff all the time though. i think there are laws with teeth and of course the immediate body to get rid of that helps surgeons maintain the integrity of their profession. when the outcome is far removed from the decision, you do get people like ministers meddling in things they don't understand and leave the consequences for the next administration.

Re: Testing Generative AI for Circuit Board Design

#162

Post by amelius » Sat, Jun 22, 2024, 11:11 AM UTC

The whole approach reminds me of:

https://gpt-unicorn.adamkdean.co.uk/

Re: Testing Generative AI for Circuit Board Design

#163

Post by amelius » Sat, Jun 22, 2024, 11:47 AM UTC

klysm wrote: post #101

amelius wrote: post #100

Can we have an AI that reads datasheets and produces Spice circuits? With the goal of building a library of simulation components.

That's the kind of thing where verification is really hard, and things will look plausible even if incorrect.

The LLM can verify e.g. transistors by looking at the curves in the datasheet.

Re: Testing Generative AI for Circuit Board Design

#164

Post by Obscurity4340 » Sat, Jun 22, 2024, 12:29 PM UTC

stavros wrote: post #34

netsec_burn wrote: post #32

Earlier quoted context omitted.

This more likely has to do with context length?

No, all the information is there, but gpt-4o tends to produce bullet points ( https://www.thesummarist.net/summary/the-making-of-a-manager... ), whereas gpt-4-turbo tends to produce much more readable prose ( https://www.thesummarist.net/summary/supercommunicators/the-... ).

How is prose more readable than bullets?

Re: Testing Generative AI for Circuit Board Design

#165

Post by stavros » Sat, Jun 22, 2024, 12:33 PM UTC

Obscurity4340 wrote: post #164

stavros wrote: post #34

Earlier quoted context omitted.

No, all the information is there, but gpt-4o tends to produce bullet points ( https://www.thesummarist.net/summary/the-making-of-a-manager... ), whereas gpt-4-turbo tends to produce much more readable prose ( https://www.thesummarist.net/summary/supercommunicators/the-... ).

How is prose more readable than bullets?

* Clearer narrative

* Connection between points

* Flows better

* Eyes don't start-stop as much

Re: Testing Generative AI for Circuit Board Design

#166

Post by klysm » Sat, Jun 22, 2024, 12:34 PM UTC

amelius wrote: post #163

klysm wrote: post #101

Earlier quoted context omitted.

That's the kind of thing where verification is really hard, and things will look plausible even if incorrect.

The LLM can verify e.g. transistors by looking at the curves in the datasheet.

The LLM can’t verify anything - it just generates what it thinks is plausible

Re: Testing Generative AI for Circuit Board Design

#167

Post by roody15 » Sat, Jun 22, 2024, 12:37 PM UTC

It makes me think of the saying “a jack of all trades a master of none”.

I cannot help but think there are some similarities between large model generative AI and human reasoning abilities.

For example if I ask a physician with a really high IQ some general questions about say anything like fixing shocks on my mini van … he may have some better ideas than me.

However he may be wrong since he specialized in medicine, although he may have provided some good overall info.

Let’s take a lower IQ mechanic who has worked as a mechanic for 15 years. Despite this human having less IQ, less overall knowledge on general topics … he gives a much better answer of fixing my shocks.

So with LLM AI fine tuning looks to be key as it is with human beings. Large data sets that are filtered / summarized with specific fields as the focus.

Re: Testing Generative AI for Circuit Board Design

#168

Post by RF_Savage » Sat, Jun 22, 2024, 12:37 PM UTC

CamperBob2 wrote: post #13

DHaldane wrote: post #10

Earlier quoted context omitted.

Update: Sonnet 3.5 is better than any other model for the circuit design and part finding tasks. Going to iterate a bit on the prompts to see how much I can push the new model on performance. Figures that any article written on LLM limits is immediately out of date. I'll write an update piece to summarize new findings.

That name threw me for a loop. 'Sonnet' already means something to EEs ( https://www.sonnetsoftware.com/ ).

Yeah same here. Thought Sonnet had added some ML stuff into their EM simulator.

Re: Testing Generative AI for Circuit Board Design

#169

Post by MOARDONGZPLZ » Sat, Jun 22, 2024, 1:16 PM UTC

Author mentions prompting techniques to get better results, presumable “you are an expert EE” or “do this and you get a digital cookie” are among these. Can anyone point me to non-SEO article that outlines the latest and greatest in the promoting techniques domain?

Re: Testing Generative AI for Circuit Board Design

#170

Post by jodrellblank » Sat, Jun 22, 2024, 2:04 PM UTC

makk wrote: post #60

surfingdino wrote: post #45

Earlier quoted context omitted.

> This feels like an excellent demonstration of the limitation of zero-shot LLMs. It feels like the wrong way to approach this. There is one posted on HN every week. How many more do we need to accept the fact this tech is not what it is sold at and we are bored waiting for it get good? I am not say "get better", because it keeps getting better, but somehow doesn't get good.

That’s a perception and the problem isn’t the AI it’s human nature: 1. every time AI is able to do a thing we move the goalposts and say, yeah, but it can’t do that other thing over there; 2. We are impatient, so our ability to get bored tends to outpace the rate of change.

> "1. every time AI is able to do a thing we move the goalposts and say, yeah, but it can’t do that other thing over there"

So are you happy that a 1940s tic-tac-toe computer "is AI"? And that's going to be your bar for AI forever?

"Moving the goalposts is a metaphor, derived from goal-based sports such as football and hockey, that means to change the rule or criterion of a process or competition while it is still in progress, in such a way that the new goal offers one side an advantage or disadvantage." - and the important part about AI is that it be easy for developers to claim they have created AI, and if we move the goalposts then that's bad because ... it puts them at an unfair disadvantage? What is even wrong with "moving the goalposts" in this situation, claiming something is/isn't AI is not a goal-based sport. The metaphor is nonsensical whining.