Wouldn't put it past somebody to code this adversarial to game their stock picks. You could weaponise misplaced trust here, no different to any other stock recommendation method. The explain part would be Fascinating. "Buy Berkshire Hathaway and apple" aside.
It's true. I was thinking about also posting requests to LLMs I use to get these recommendations. But again, I can lie about answers. I wonder if there is a way to make it 100% transparent (or reproducible).
