<div dir="ltr">Learning to?  They've been able to for a while already.</div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Sat, Jun 7, 2025 at 9:33 PM BillK via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org">extropy-chat@lists.extropy.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Godfather of AI Alarmed as Advanced Systems Quickly Learning to Lie,<br>
Deceive, Blackmail and Hack.<br>
"I’m deeply concerned by the behaviors that unrestrained agentic AI<br>
systems are already beginning to exhibit."<br>
Jun 7, 2025 by Noor Al-Sibai<br>
<br>
<<a href="https://futurism.com/ai-godfather-lying-deception" rel="noreferrer" target="_blank">https://futurism.com/ai-godfather-lying-deception</a>><br>
Quote:<br>
In a blog post announcing LawZero, the new nonprofit venture, "AI<br>
godfather" Yoshua Bengio said that he has grown "deeply concerned" as<br>
AI models become ever more powerful and deceptive.<br>
<br>
"This organization has been created in response to evidence that<br>
today's frontier AI models have growing dangerous capabilities and<br>
[behaviors]," the world's most-cited computer scientist wrote,<br>
"including deception, cheating, lying, hacking, self-preservation, and<br>
more generally, goal misalignment."<br>
-----------------<br>
<br>
Hmmm. That sounds like he is worried that AI models are becoming too<br>
much like humans............<br>
<br>
BillK<br>
<br>
_______________________________________________<br>
extropy-chat mailing list<br>
<a href="mailto:extropy-chat@lists.extropy.org" target="_blank">extropy-chat@lists.extropy.org</a><br>
<a href="http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat" rel="noreferrer" target="_blank">http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat</a><br>
</blockquote></div>