it's an interesting point; you do of course have to add those electrons to the metal atoms in the first place when you're smelting it from ore, unless you're working from a rare native metal deposit, and plausibly you could leach metal ions out of ore and feed them into your 3-d printer. i suspect that the tests they've done so far, however, are using reagent-grade metal salts from sigma-aldrich or similar with much more embodied energy than metallurgical-grade copper or whatever