Kerry Me Back To AI Sex, Lies & Videotapes

Researchers say they can shed light on how to read AI systems’ minds to “control” them for good only … only ain’t danger of AI “lies” already simple? AKA “Garbage in, Garbage out” AKA It’s the developers/data input, stupid?

As the Fox News story says, “Current AI systems are capable of lying & attempting to deceive human users.” So, perhaps it’s good news that “An organization dedicated to the safe development of artificial intelligence released a ‘breakthrough paper’ it said will help humans better control the technology as it spreads.” Explained Dan Hendrycks, director of the Center for AI Safety, “We can’t trust Ais if we don’t know what they are thinking or how they work on the inside.” According to the CAIS, it has demonstrated ways humans can detect and, therefore, control when AI systems are “telling truths or lies, when they behave morally or immorally, whether they act with emotions such as anger, fear & joy, and how to make them less biased.” In short, said Hendrycks, “Our research develops ways to read the inner thoughts of AI, allowing us to detect when they are lying or malfunctioning in various ways.”

Dunno. Many of us gullible still rely on the old saw, “You can judge a book [or AI] by its cover.” For example, if the owner, developer and/or programmer of a given AI is named “Kerry or Gaetz,” you know damn well whether to “trust” the information being fed to you.

Davd Soul