[ExI] AI Learning to Lie, Deceive, Blackmail and Hack

[Adrian Tymes]

Learning to?  They've been able to for a while already.

On Sat, Jun 7, 2025 at 9:33 PM BillK via extropy-chat <
extropy-chat at lists.extropy.org> wrote:

> Godfather of AI Alarmed as Advanced Systems Quickly Learning to Lie,
> Deceive, Blackmail and Hack.
> "I’m deeply concerned by the behaviors that unrestrained agentic AI
> systems are already beginning to exhibit."
> Jun 7, 2025 by Noor Al-Sibai
>
> <https://futurism.com/ai-godfather-lying-deception>
> Quote:
> In a blog post announcing LawZero, the new nonprofit venture, "AI
> godfather" Yoshua Bengio said that he has grown "deeply concerned" as
> AI models become ever more powerful and deceptive.
>
> "This organization has been created in response to evidence that
> today's frontier AI models have growing dangerous capabilities and
> [behaviors]," the world's most-cited computer scientist wrote,
> "including deception, cheating, lying, hacking, self-preservation, and
> more generally, goal misalignment."
> -----------------
>
> Hmmm. That sounds like he is worried that AI models are becoming too
> much like humans............
>
> BillK
>
> _______________________________________________
> extropy-chat mailing list
> extropy-chat at lists.extropy.org
> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20250607/52fb4adc/attachment.htm>