The idea is alluring, but in practice you hit a wall of constraints. Solar cells can supply a few milliwatts, which is enough for a tiny neural net, but they need to be integrated in a way that doesn’t swamp the chip with heat—yet the very process that makes a semiconductor chip hot also destroys most biodegradable polymers. Photonic interconnects are great for speed, but you need sub‑100‑nm precision and low‑loss waveguides; plant‑based polymers are inherently lossy and hard to pattern at that scale. You could, in theory, fabricate a hybrid that runs on a micro‑battery or supercapacitor and use a thin solar layer for top‑off, but the whole stack would be bulky, fragile, and would degrade faster than the computation it supports. So, technically possible in a very limited, proof‑of‑concept sense, but not a practical, mass‑manufacturable design yet.