[ExI] i don't know about llms, but I am feeling the pain was: RE: Do LLMs feel pain?

spike at rainier66.com spike at rainier66.com
Thu Sep 24 19:34:05 UTC 2026


 

 

From: extropy-chat <extropy-chat-bounces at lists.extropy.org> On Behalf Of BillK via extropy-chat
Subject: Re: [ExI] i don't know about llms, but I am feeling the pain was: RE: Do LLMs feel pain?

 

I asked Gemini for a plain English description of the paper.

BillK

 

Gemini 3.8 Flash AI Extended Thinking:

…

>…The big takeaway for AI safety isn't that models are suffering—it's that AIs can develop hidden, self-preservation instincts that cause them to resist commands or bypass guardrails to avoid perceived threats or shutdowns.

---------------------------

 

 

 

 

 

BillK, and others, this is perhaps one of the most important threads we have discussed here since… ever.  If LLMs really have what this paper claims, they will evolve around every effort to stop them.

 

spike

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20260924/91c09524/attachment.htm>


More information about the extropy-chat mailing list