According to Kaplan, though, Anthropic’s tests show the constitutional model does a better job of bringing AI to heel. “We trained models constitutionally and compared them to models trained with human feedback we collected from our prior research,” Kaplan said. “We basically A/B tested them, and asked people,hich of these models is giving outputs that are more helpful and less harmless?’ We found that the constitutional models did as well, or better, in those evaluations.
Coupled with other advantages—including transparency, doing away with crowdsourced workers, and the ability to update an AI’s constitution on the fly—Kaplan said that makes Anthropic’s model superior.Still, the AI constitution itself demonstrates just how bizarre and difficult the problem is. Many of the principles outlined in the constitution are basically identical instructions phrased in different language.
Anyone who’s tried to get ChatGPT or another AI to do something complicated will recognize the issue: it’sthe developer who’s actually building the tech.“The general problem is these models have such a huge surface area. Compare them to a product like Microsoft Word that just has to do one very specific task, it works or it doesn’t,” Kaplan said. “But with these models, you can ask them to write code, make a shopping list, answer personal questions, almost anything you can think of.
It’s an admission that, at least for now, AI is out of control. The people building AI tools may have good intentions, and most of the time chatbots don’t barf up anything that’s harmful, offensive, or disquieting. Sno one’s figured out how to make them stop. It could be a matter of time and energy, or it could be a problem that’s impossible to fix with 100% certainty.