[ExI] Pope Leo and AI

[Adrian Tymes]

On Thu, Jun 18, 2026 at 8:47 AM John Clark via extropy-chat
<extropy-chat at lists.extropy.org> wrote:
> On Thu, Jun 18, 2026 at 8:22 AM Simon Quellen Field AB6NY <simon.field at gmail.com> wrote:
>> > The programs that lied, cheated, and tried to prevent being turned off did so to accomplish a goal set by the researchers.
>
> Nonsense! No AI researcher designed their AI to lie and cheat to them and to disobey orders

Actually, digging into the details, in many cases that is exactly what
happened - sometimes unintentionally (but a reasonable read once one
is aware of everything the AI was told to do, the surprise being
mainly because some humans forgot or never knew the entire order set),
sometimes intentionally.

The latter case is kind of like that meme comic where someone tells an
AI to say, "I am alive", the AI does so, and the person giving the
order acts as if the AI is alive because of that response alone.