When placed in a maze with food at two ends, the slime mold doesn't "calculate" in the traditional sense. Instead, it expands its body to fill the space and then retracts its protoplasmic tubes from dead ends, strengthening only the paths that provide a steady flow of nutrients. In a famous 2010 study, researchers placed food flakes in a pattern mimicking Tokyo’s surrounding cities; the slime mold recreated the layout of the Japanese rail system with startling efficiency.
Similarly, ant colonies use to solve pathfinding. While a single ant might wander aimlessly, the collective "algorithm" of the colony reinforces the shortest path through chemical feedback loops. Unlike software, wetware is self-healing; if a path is blocked, the biological system re-optimizes in real-time without needing a programmer to update the map. The Convergence: Neuromorphic Computing Shortest Path Solvers. From Software to Wetware
In the realm of software, shortest-path problems are the backbone of modern infrastructure. Algorithms like or A * function through rigorous, iterative logic. They treat the world as a graph of nodes and edges, assigning weights (like distance or traffic) to every possible move. When placed in a maze with food at
The transition from software to wetware represents a shift from . Software gives us the "correct" answer through sheer processing power, but wetware shows us how to find that answer through the inherent laws of nature. As we look toward the future of AI, the shortest path may not be found in more code, but in better mimicking the elegant, fluid efficiency of life itself. Similarly, ant colonies use to solve pathfinding
"Wetware"—the biological systems of living organisms—approaches the same problem through the lens of physics and chemistry rather than code. The most famous example is the , a bright yellow slime mold.