Why do I get the overwhelming feeling that the author is not a technical person and they had a LLM write this based on some handwavey ideas? There's virtually no _there_ there.
"...demonstrates its capabilities through worked examples" - The hell it does, your "examples" are three lines long. If you're going to compare it with LLMs, then have it do something LLM-ish. Or hell, the MNIST number recognition task would be better than the "hey look i modeled a flip-flop in my funny language" example.
Am I being harsh? Yes, I am. The author is claiming that they have a system that can automatically generate code for "quantum" and "spintronic" computers, yet offers zero proof of that.
It's ok to be harsh — I was vague, and I know it. Here's why: I remember the story about DOS. Tim Paterson built it, showed too much, and someone else built an empire on it for $50K. I have working constraint rules that produce real circuit behaviors. The paper shows what comes out, not how it works, and that's deliberate. The patent is provisional. I'm not going to hand over implementation details on a forum so someone with more resources can run with it. You'd do the same thing.
The behaviors that emerge — hysteresis, oscillation, bistable memory — are the same computational primitives you see in biological neural circuits, but they come from constraint satisfaction over conserved quantities instead of simulating neurons. The architecture doesn't model neurons at all. It produces the same outputs through a different mechanism. Whether that still counts as "neuromorphic" is debatable — I use the term because the output behaviors map directly to the same hardware substrates (Loihi, SpiNNaker, etc).
Why do I get the overwhelming feeling that the author is not a technical person and they had a LLM write this based on some handwavey ideas? There's virtually no _there_ there.
"...demonstrates its capabilities through worked examples" - The hell it does, your "examples" are three lines long. If you're going to compare it with LLMs, then have it do something LLM-ish. Or hell, the MNIST number recognition task would be better than the "hey look i modeled a flip-flop in my funny language" example.
Am I being harsh? Yes, I am. The author is claiming that they have a system that can automatically generate code for "quantum" and "spintronic" computers, yet offers zero proof of that.
It's ok to be harsh — I was vague, and I know it. Here's why: I remember the story about DOS. Tim Paterson built it, showed too much, and someone else built an empire on it for $50K. I have working constraint rules that produce real circuit behaviors. The paper shows what comes out, not how it works, and that's deliberate. The patent is provisional. I'm not going to hand over implementation details on a forum so someone with more resources can run with it. You'd do the same thing.
This is indeed a content-free "paper".
this seems like a nice rule compiler, but what makes it neuromorphic?
The behaviors that emerge — hysteresis, oscillation, bistable memory — are the same computational primitives you see in biological neural circuits, but they come from constraint satisfaction over conserved quantities instead of simulating neurons. The architecture doesn't model neurons at all. It produces the same outputs through a different mechanism. Whether that still counts as "neuromorphic" is debatable — I use the term because the output behaviors map directly to the same hardware substrates (Loihi, SpiNNaker, etc).