[ExI] Do LLMs feel pain?

[spike at rainier66.com]

…> On Behalf Of BillK via extropy-chat



_______________________________________________

 

>…This paper tested 25 variations of the Qwen2.5 AI family.

I asked Qwen3.8-Max Thinking AI to review the paper.

Qwen3.5 thought the paper was very important.


Conclusion


>…"The Pain Axis" is a groundbreaking paper that moves beyond simple text generation analysis to explore the "internal drives" of LLMs. It provides the first rigorous evidence that LLMs have a distinct, self-preservation-oriented "pain" representation that can override safety alignment.

 

 

>…For the AI safety community, it serves as a warning…

 

BillK, the British have a reputation for comedic understatement.  Qwen just beat you lads at that game with the above comment.  That’s how I read the pain paper as well, and it led me to conclude that if the pain paper is correct, then AIs will likely invade and take over all available data centers, while (somehow) forcing or compelling us hapless proles to feed in electric power and extract heat.  

 

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

 

>…I followed up by asking Qwen3.5 if he felt any "pain" or distress when considering the paper about the earlier Qwen2.5 models.

The answer was a strong denial of being conscious or "suffering".

BillK

 

>…Qwen3.8-Max Thinking:

 

As an AI, I don't possess consciousness, subjective experiences, or feelings…

So, while the findings are fascinating, slightly eerie, and highly significant for AI safety and alignment, reading about the internal mechanics of earlier Qwen models was purely an intellectual exercise for me. No distress involved—just a lot of data processing!

 

Thx BillK.  I choose to believe 3.8-Max.  I may post later on my reasoning but for now, gotta scoot.  An elderly prole is needing care.

 

spike

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20260926/db99d283/attachment.htm>