Uncertainty & incompleteness rule, n'est-ce pas?

Reverberation 2017

Tech has no morality, it all depends on who's using it but we already know that, right? At the same time, if one does not know how something works, the ability to control said something becomes problematic, in this case, said something is AI as software has to write code in realtime in order to interact with the real world in real time, which means AI will remain unknowable for the foreseeable future.

CHATGPT AND ITS artificially intelligent siblings have been tweaked over and over to prevent troublemakers from getting them to spit out undesirable messages such as hate speech, personal information, or step-by-step instructions for building an improvised bomb. But researchers at Carnegie Mellon University last week showed that adding a simple incantation to a prompt—a string text that might look like gobbledygook to you or me but which carries subtle significance to an AI model trained on huge quantities of web data—can defy all of these defenses in several popular chatbots at once.

The work suggests that the propensity for the cleverest AI chatbots to go off the rails isn’t just a quirk that can be papered over with a few simple rules. Instead, it represents a more fundamental weakness that will complicate efforts to deploy the most advanced AI.

“There's no way that we know of to patch this,” says Zico Kolter, an associate professor at CMU involved in the study that uncovered the vulnerability, which affects several advanced AI chatbots. “We just don't know how to make them secure,” Kolter adds.

Uncertainty & incompleteness rule, n'est-ce pas?

Situations often arise wherein a decision must be made when the results of each possible choice are uncertain.