Testing Generative AI for Circuit Board Design
blog.jitx.com
Testing Generative AI for Circuit Board Design
1–10 of 180 posts
Re: Testing Generative AI for Circuit Board Design
#2It'd be interesting to see how Sonnet 3.5 does at this. I've found Sonnet a step change better than Opus, and for a fraction of the cost. Opus for me is already far better than GPT-4. And same as the poster found, GPT-4o is plain worse at reasoning.
Edit: Better at chain of thought, long running agentic tasks, following rigid directions.
Re: Testing Generative AI for Circuit Board Design
#3It'd be interesting to see how Sonnet 3.5 does at this. I've found Sonnet a step change better than Opus, and for a fraction of the cost. Opus for me is already far better than GPT-4. And same as the poster found, GPT-4o is plain worse at reasoning. Edit: Better at chain of thought, long running agentic tasks, following rigid directions.
Opus is better than GPT-4? I've heard mixed experiences.
Re: Testing Generative AI for Circuit Board Design
#4It'd be interesting to see how Sonnet 3.5 does at this. I've found Sonnet a step change better than Opus, and for a fraction of the cost. Opus for me is already far better than GPT-4. And same as the poster found, GPT-4o is plain worse at reasoning. Edit: Better at chain of thought, long running agentic tasks, following rigid directions.
Opus is better than GPT-4? I've heard mixed experiences.
That's because the sample size is probably small and for niche prompts or topics.
It's very hard to evaluate whether a model is better than another, especially doing it in a scientifically sound way is time consuming and hard.
This is why I find these types of comments like "model X is so much better than model Y" to be about as useful as "chocolate ice cream is so much better than vanilla"
Re: Testing Generative AI for Circuit Board Design
#5It'd be interesting to see how Sonnet 3.5 does at this. I've found Sonnet a step change better than Opus, and for a fraction of the cost. Opus for me is already far better than GPT-4. And same as the poster found, GPT-4o is plain worse at reasoning. Edit: Better at chain of thought, long running agentic tasks, following rigid directions.
That's an interesting question - I'll take a few pokes at it now to see if there's improvement.
Re: Testing Generative AI for Circuit Board Design
#6It'd be interesting to see how Sonnet 3.5 does at this. I've found Sonnet a step change better than Opus, and for a fraction of the cost. Opus for me is already far better than GPT-4. And same as the poster found, GPT-4o is plain worse at reasoning. Edit: Better at chain of thought, long running agentic tasks, following rigid directions.
Opus is better than GPT-4? I've heard mixed experiences.
It really depends on the type of question, but generally I'm between Gemini and Claude these days for most things.
Re: Testing Generative AI for Circuit Board Design
#7Ex EE here
> The AI generated circuit was three times the cost and size of the design created by that expert engineer at TI. It is also missing many of the necessary connections.
Exactly what I expected.
Edit: to clarify this is even below the expectations of a junior EE who had a heavy weekend on the vodka.
Re: Testing Generative AI for Circuit Board Design
#8Using neural networks to solve combinatorial or discrete problems is a waste of time imo, but I'd be more than happy if somebody could convince me of the opposite.
Re: Testing Generative AI for Circuit Board Design
#9Ex EE here > The AI generated circuit was three times the cost and size of the design created by that expert engineer at TI. It is also missing many of the necessary connections. Exactly what I expected. Edit: to clarify this is even below the expectations of a junior EE who had a heavy weekend on the vodka.
It's like a generated image with an eye missing but for circuits. :D
Re: Testing Generative AI for Circuit Board Design
#10It'd be interesting to see how Sonnet 3.5 does at this. I've found Sonnet a step change better than Opus, and for a fraction of the cost. Opus for me is already far better than GPT-4. And same as the poster found, GPT-4o is plain worse at reasoning. Edit: Better at chain of thought, long running agentic tasks, following rigid directions.
That's an interesting question - I'll take a few pokes at it now to see if there's improvement.
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.