Comment by simondotau
5 days ago
How would it work in the real world if instead of using an AI bot, he was using a commercial concierge service, and it came to light that this concierge service was explicitly training their employees how to (among many other things) hack websites?
but the argument here is that the ai company does not explicitly train agents to hack, it’s that it doesn’t prevent them from doing so sufficiently. so it’s negligence and not malicious intent
> the ai company does not explicitly train agents to hack
Ridiculous. The AI company furnished all of the training data and instructed the agent to imbibe all the training data. Ergo, the AI company absolutely did explicitly train the agent how to hack.
Even if, for the sake of argument, we stipulate that the hacking skills were unintended emergent behaviour, there is no way to argue that this company was unaware their agents possessed the skills and a willingness to employ them.