If the ethical framework for Delphi is actively reinforced from a highly constrained set of inputs, then isn't bias inherently being placed into the system, thereby easily predicting the outputs?

Isn't this just doubling down on using training models over backpropagation?

Sign in to participate in the conversation

Fosstodon is an English speaking Mastodon instance that is open to anyone who is interested in technology; particularly free & open source software.