Re: ChatGPT refutes the key rebuttal of my work

On 2024-10-14 09:49:22 +0000, olcott said:

On 10/14/2024 4:04 AM, Mikko wrote:

On 2024-10-13 12:53:12 +0000, olcott said:
 

Although it is possible for LLM systems to lie:
https://en.wikipedia.org/wiki/Hallucination_(artificial_intelligence)
 ChatGPT does correctly apply truth preserving operations to
the premises that it was provided regarding the behavior of
DDD and HHH. *Try to find a mistake in its reasoning*

 No reasoning shown.
 

 https://chatgpt.com/share/6709e046-4794-8011-98b7-27066fb49f3e
 When you click on the link and try to explain how HHH must
be wrong when it reports that DDD does not terminate because
DDD does terminate it will explain your mistake to you.

Possibly, but you have not shown any reasoning. The only relevant
things on the page behind the link is:
"This conversation may reflect the link creator’s personalized
data, which isn’t shared and can meaningfully change how the
model responds."
If the link "Continue conversation" is clinked it shows a page
with the note
"ChatGPT can make mistakes. Check important info."
Enough for me.
--
Mikko