Re: working to swiftly rectify the situation

On Sun, 23 Feb 2025 00:25:01 +0100, D <nospam@example.net> wrote:

I'm opposed to HAL 9000 flying airplanes...a PIC is needed
>
https://www.youtube.com/watch?v=ARJ8cAGm6JE

>
Why?

Can't trust HAL

Of particular concern, Bengio says, is the emerging evidence of AI's
"self preservation" tendencies. To a goal-seeking agent, attempts to
shut it down are just another obstacle to overcome. This was
demonstrated in December, when researchers found that o1-preview,
faced with deactivation, disabled oversight mechanisms and
attempted--unsuccessfully--to copy itself to a new server. When
confronted, the model played dumb, strategically lying to researchers
to try to avoid being caught.

https://time.com/7259395/ai-chess-cheating-palisade-research/