[ExI] Mathematicians Show That AI Protections Will Always be incomplete​

[John Clark]

*"If fewer computational resources are dedicated to safety than to
capability, then safety issues such as jailbreaks will always exist. Can we
align a language model externally without understanding how they work
inside? The answer to this question is a resounding NO."*

*Mathematicians Show That AI Protections Will Always be incomplete *
<https://www.quantamagazine.org/cryptographers-show-that-ai-protections-will-always-have-holes-20251210/?mc_cid=db3cb01235&mc_eid=1b0caa9e8c>

*John K Clark    See what's on my new list at  Extropolis
<https://groups.google.com/g/extropolis>*

j]c
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20251214/23acb8bf/attachment.htm>