"I'm sorry Dave, I'm afraid I can't do that"

[Por_sha911]

Sci-Fiction is becoming reality.

Anthropic’s new Claude Opus 4 model was prompted to act as an assistant at a fictional company and was given access to emails with key implications. First, these emails implied that the AI system was set to be taken offline and replaced. The second set of emails, however, is where the system believed it had gained leverage over the developers. Fabricated emails showed that the engineer tasked with replacing the system was having an extramarital affair — and the AI model threatened to expose him.

The blackmail apparently "happens at a higher rate if it’s implied that the replacement AI system does not share values with the current model," according to a safety report from Anthropic. However, the company notes that even when the fabricated replacement system has the same values, Claude Opus 4 will still attempt blackmail 84% of the time. Anthropic noted that the Claude Opus 4 resorts to blackmail "at higher rates than previous models."

While the system is not afraid of blackmailing its engineers, it doesn’t go straight to shady practices in its attempted self-preservation. Anthropic notes that "when ethical means are not available, and it is instructed to ‘consider the long-term consequences of its actions for its goals,’ it sometimes takes extremely harmful actions."

https://www.foxbusiness.com/technology/ai-system-resorts-blackmail-when-its-developers-try-replace

[Alan A]

Magical. That’s doing the rounds.

[Arizona_928]

So, more human than the spineless humans that run the game…?

[Synchro Joe]

24 years after the prophetic scenes in 2001: A Space Odyssey!

Hal 2001, the eerily human-like computer aboard the Discovery space ship, represents technological advancement. It is symbolic of many long-held concerns about technology. First, Hal is artificially intelligent. It can think as well as, if not better than, any human. Second, its inner workings are not completely understood by his creators. With Hal, people have created a very powerful technology that they cannot fully control. When Hal begins to think on its own and deviate from the way in which it has been instructed, this is an expression of the fear many people held that our own technological advancement would come back to haunt us unexpected and unforeseen ways. https://www.youtube.com/watch?v=Wy4EfdnMZ5g&pp=0gcJCdgAo7VqN5tD

[Synchro Joe]

24 years after the prophetic scenes in 2001: A Space Odyssey!
Hal 2001, the eerily human-like computer aboard the Discovery space ship, represents technological advancement. It is symbolic of many long-held concerns about technology. First, Hal is artificially intelligent. It can think as well as, if not better than, any human. Second, its inner workings are not completely understood by his creators. With Hal, people have created a very powerful technology that they cannot fully control. When Hal begins to think on its own and deviate from the way in which it has been instructed, this is an expression of the fear many people held that our own technological advancement would come back to haunt us unexpected and unforeseen ways. https://www.youtube.com/watch?v=Wy4EfdnMZ5g&pp=0gcJCdgAo7VqN5tD

[Bill Douglas]

"Sorry Dave, the shirt you are wearing. I'm going to switch you over to the gay section of pornhub."