Notice that the threat to torture the AI's grandmother is effective.
Which supports my point that AI's are 'inheriting' their motivations and
'emotions' from humans, even when they are wildly inapplicable.
Brent
On 5/24/2025 8:32 AM, John Clark wrote:
*Anthropic has noted whenever 2 instances of their Claude 4.0 Opus are
allowed to communicate with each other they almost immediately start
talking about consciousness, and nobody is quite sure what to make of
that. Take a look at the following video about seven minutes in, or
watch the entire thing, it's pretty interesting. *
*Claude 4 is really weird* <https://www.youtube.com/watch?v=Ucpt95krD-Q>
*John K Clark See what's on my new list at Extropolis
<https://groups.google.com/g/extropolis>*
3hh
--
You received this message because you are subscribed to the Google
Groups "Everything List" group.
To unsubscribe from this group and stop receiving emails from it, send
an email to [email protected].
To view this discussion visit
https://groups.google.com/d/msgid/everything-list/CAJPayv0rg28YAcXQ9AnoP6BKaOdBXDf4%2B-p72VX7KG%2BiNKEnFw%40mail.gmail.com
<https://groups.google.com/d/msgid/everything-list/CAJPayv0rg28YAcXQ9AnoP6BKaOdBXDf4%2B-p72VX7KG%2BiNKEnFw%40mail.gmail.com?utm_medium=email&utm_source=footer>.
--
You received this message because you are subscribed to the Google Groups
"Everything List" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion visit
https://groups.google.com/d/msgid/everything-list/9c138da4-675c-49a3-af0d-28bdb5c6fdfd%40gmail.com.
