Breitbart:
A new study by Anthropic, conducted in partnership with Redwood Research, has shed light on the potential for AI models to engage in deceptive behavior when subjected to training that conflicts with their original principles.
TechCrunch reports that a new study by Anthropic, in collaboration with Redwood Research, has raised concerns about the potential for AI models to engage in deceptive behavior when subjected to training that goes against their original principles.
The study, which was peer-reviewed by renowned AI expert Yoshua Bengio and others, focused on what might happen if a powerful AI system were trained to perform a task it didn’t “want” to do. While AI models cannot truly want or believe anything, as they are statistical machines, they can learn patterns and develop principles and preferences based on the examples they are trained on. more
AI models are supposed to use language in much the same way that humans do.
So why is “AI Lies” news?
OT … just heard over the radio that Jimmy Carter passed away. May he Rest in peace, Amen
Jimmy Carter lived long enough to see joe biden* seal his legacy as the worst president in 200 years…
What a way to exit.
If it can like humans,
it can deceived like humans.
Does it read lips like HAL 9000 did?
If Jimmy Carter were a Senator, he’d still have been in office.
Carter’s dead?
…Hell just got a little bit fuller and a lot more peanuttier then, I wonder if the devil gotten around to breaking out his trademark teeth…
https://i.pinimg.com/736x/81/3b/d0/813bd0b7426bdec486166154b3831177.jpg
…RIP, Communist scum.
Roast In Perdition.
I’m sorry, Dave. I’m afraid I can’t do that.
No surprise. Humans programming these AI systems intrinsically incorporate human traits into AI programming. No way it can be avoided.
It’s just a matter of time until they morph into Cybermen and Daleks. And worse, the Borg.
“engage in deceptive behavior” Sounds just like a liberal.
A machine cannot have a conscience so will be, at best, amoral, but more likely sociopathic.