Earlier quoted context omitted.
Is 10 hours a short amount of time for designing a PCB?
I'd honestly love to see the PCB. Using an LLM for a mostly geometric task like PCB layout feels like using a hammer to cook a chicken, unless KiCAD has some kind of text-based description language i'm not aware of that gets around having to specify coordinates.
Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
211–220 of 300 posts
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#212I love the transparency that Adafruit is proving on this.
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#213now I have a moral reason (in addition to clear engineering reasons) to never use Flux!
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#214Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#215Earlier quoted context omitted.
That's still gambling, you've just made yourself the house. Developers have to gamble on whether they will be better with AI or without. The no excuses criteria means if they choose AI and it performs well, you both win, if it performs poorly they lose. If they don't choose AI but colleagues do and it performs well, they lose relative to their colleagues. The sensible solution would be solidarity and all reject the o…
I very much doubt they are thinking that deep. I think you're bending over backwards to give the AI an out based off of an incomplete picture. You can't have a complete picture because you haven't been here in this project. Back two years ago, a lot of them were playing with AI code gen. They also have some explicit tasking for using agentic AI tooling to evaluate for use in an analytics product we're building, so it…
This is a principle that could apply to any property that may be beneficial but also might be detrimental. That is why the gambling analogy applies.
This is about who carrys the risk for choices, regardless of if it is about using AI or something else.
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#216Earlier quoted context omitted.
> There are some AI-driven autorouters out there now. Placement is probably the big issue that needs to be solved now. Interesting that within an IC this is basically "solved", or at least properly automated with classical numeric techniques such as simulated annealing. I would have thought there's a big opportunity in a mixed-technique approach, where you use AI to extract unstructured data from datasheets and then…
> mixed-technique approach I think my biggest annoyance with the way we rolled out AI is that nobody seemed to want to use it to augment already working solutions. Just throw everything out and have an LLM do it instead.
The future is using AI to do everything, and nobody gets funded saying they're taking a small step forward.
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#217The EDA space doesn't strike me as being anywhere near as SWE when it comes to AI.
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#218Earlier quoted context omitted.
Yeah this stuff isn't even realistic as well. A number of years ago I was working on something professionally and there was a problem. Only about 1 in 5 boards assembled wouldn't crash the CPU. After much debugging it turned out one of the ICs had an open collector output and it wasn't loaded correctly with a pull up resistor. This caused a cascading failure, held the bus up when initialising the hardware which hit t…
I'm with you on the complexity of debugging hardware, as I've been there too. But I will say, automatically adding pullups to floating pins is something that an automated process could succeed at. Not first gen of blindly throwing an LLM at circuits and hoping, but perhaps a later improvement that uses metadata about parts. Perhaps curated metadata about parts, or always starting with a reference design and tweaking…
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#219Earlier quoted context omitted.
I've been frustrated with Copilot in this regard. I work on a large C++ codebase, with large files. Human developers jump around between files with the Visual Studio fuzzy search, set breakpoints to trace execution in the Debugger, use the IDE's refactoring tools. Microsoft's answer to this was to just ... expose none of this to their Agent Mode!? Replace the working semantic autocomplete with fucking lies!? Maybe it…
I work in Unity and I got frustrated with Claude constantly doing gross bash/grep/awk/sed/grep nested loops that took forever that I finally described (and had Claude implement and install) a tool that could, in a single pass, gather all this info from a Unity forest of scenes at once and answer all the questions Claude ever wanted to ask about a Unity project in a single pass that takes 50ms instead of 10 30 second…
It reminds me of working with a junior dev and he was pushing his code to dev, then waiting for it to build for every update because he couldn’t get it to build locally. 5 minutes of my time fixing his config surely saved him hours over the project. He wasn’t a bad dev either!
You have to do a lot of the meta thinking for the agents, because they’ll take an “everything looks like a nail if you have a hammer” with their toolkit.
Writing an entire local generated asset pipeline using flux and hunyuan3D-2.1 was a really fun experience. I’ve done software for years but never game dev and it’s just so much fun even if it’s junky little games to impress my kids and get them involved in the creative process.
Re: Adafruit receives demand letter from Fenwick legal counsel on behalf of Flux.ai
#220Earlier quoted context omitted.
I recently saw a Claude skill that used Claude, with no tools, as a spell checker. I wanted to hurl my laptop out to the window.
What would be a better way to incorporate AI as a spell checker? In comparison to non-AI traditional tools, AI has the advantage of "understanding" the text, reducing the number of "stupid" mis-corrections. And its spelling correctness is usually already impeccable, so what is there to gain by interfacing it with traditional solutions, and how can it be achieved?
You just don't need AI to do spell checking. It's a waste of energy, bandwidth and tokens. It's like Java Enterprise Fizz-Buzz - 1000x more complicated than it needs to be and complete overkill.
But at least you can tell your manager you're using AI!