"hardware as fast as software". Please no, lol. I've imagined a chip running as slow as python.
haha nice catch but this is about development speed
Show HN: Copperhead – Cursor for circuit boards
81–90 of 121 posts
Re: Show HN: Copperhead – Cursor for circuit boards
#82Earlier quoted context omitted.
Computationally what’s the difference between a human and an LLM besides scale and speed? Trained humans are still using heuristics and shortcuts. Just because these are subconscious and only possessed by talented, trained professionals doesn’t make the skill computationally special.
LLM do not think because they are not real "AI", but it does copy the linear patterns people exhibit if statistically salient within the granularity of the higher dimensional vector search space proximity. Watermarking does skew the compaction slightly, but not far from resulting output patterns. =3 https://en.wikipedia.org/wiki/The_Subservient_Chicken
The LLM would learn the heiristics (example: data lines first, power lines later, etc.) and would request the autorouter to do that routing, then take the image output and request a different part (depth-first). If later no routing is posible with that configuration, after some retries it could try another way.
It wouldn't solve complex boards, and engineers are always needed for short comings (and even if not, for research), but I wouldn't say this is something different than poetry, music or pixel art, LLMs can imitate although most of the times in a uncanny way.
Re: Show HN: Copperhead – Cursor for circuit boards
#83Earlier quoted context omitted.
I use a jigsaw to cut wood. It works pretty good. What’s the point of a table saw?
You joke but my coping saw cuts wood much faster than any of my normal saws. I don't know a lot about saws, I presume it's the type of blade on it. And I do indeed have three saws, which is a lot for someone who doesn't know much about saws. One that says it's good for cutting metal, one for wood and one for tight corners in wood (a coping saw).
Re: Show HN: Copperhead – Cursor for circuit boards
#84[flagged]
Re: Show HN: Copperhead – Cursor for circuit boards
#85This is probably not the primary way people use the tool, but if I log in (desktop, Chrome on macOS), click "Start a board" on the sidebar, and go to click any of the inputs, I can't type text in them (the inputs are "Start from an example", "What are you building", and "The brief".
Re: Show HN: Copperhead – Cursor for circuit boards
#86https://github.com/deadbringer17/Copperbrain
They have similar names, seem to solve similar problems and both have first commit within a few days in July. One is Python and the other Typescript though and they don't seem to be forks.
Re: Show HN: Copperhead – Cursor for circuit boards
#87"hardware as fast as software". Please no, lol. I've imagined a chip running as slow as python.
Re: Show HN: Copperhead – Cursor for circuit boards
#88[flagged]
Please don't post shallow dismissals or focus on trivialities. Let's focus on the substance of the project. It's a good sign that an early stage project hasn't devoted a lot of time or cost into their logo.
I understand—these days, there are more reasons to vibe a landing page than not. To many, however, this page is going to be their first encounter with the project. While it sure is shallow to judge a book solely by its cover, in this case, the cover just blatantly screams "we haven't even tried"... Can you really blame people for not looking beyond it if even its own creator gave it a similar amount of attention? Especially in 2026, when everything preys on your attention and generating plausibly-looking low-effort projects has never been easier?
Re: Show HN: Copperhead – Cursor for circuit boards
#89Can I take the output of this and get a fully assembled board mailed to me? Thats my dream...
Its maybe more hands on than you want it to be, but you mostly just need to supervise the work. But yes, the CAD outputs go directly to the JLCPCB ordering form, or whereever you fab
Re: Show HN: Copperhead – Cursor for circuit boards
#90Earlier quoted context omitted.
Computationally what’s the difference between a human and an LLM besides scale and speed? Trained humans are still using heuristics and shortcuts. Just because these are subconscious and only possessed by talented, trained professionals doesn’t make the skill computationally special.
LLM do not think because they are not real "AI", but it does copy the linear patterns people exhibit if statistically salient within the granularity of the higher dimensional vector search space proximity. Watermarking does skew the compaction slightly, but not far from resulting output patterns. =3 https://en.wikipedia.org/wiki/The_Subservient_Chicken