Forums before death by AOL, social media and spammers... "We can't have nice things"
|    sci.physics.relativity    |    The theory of relativity    |    225,861 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 224,401 of 225,861    |
|    Chris M. Thomasson to olcott    |
|    Re: OpenAI is Toast: Kimi K2 is Live [Ha    |
|    10 Nov 25 12:08:55    |
   
   XPost: sci.math, sci.logic   
   From: chris.m.thomasson.1@gmail.com   
      
   On 11/10/2025 10:20 AM, olcott wrote:   
   > On 11/10/2025 8:57 AM, Mild Shock wrote:   
   >> Hi,   
   >>   
   >> Lets analyse Ross Finlaysons Halting Problem   
   >> nonsensen with Kimi K2:   
   >>   
   >> Ross Finlayson schrieb:   
   >> > I don't go looking for paradoxes,   
   >> > since there aren't any in a real theory,   
   >> > contradictions though automatically   
   >> > make for counterexamples, then about   
   >> > the "analytical bridges",   
   >> > or ponts is what I call them,   
   >> > not the "invincible ignorance".   
   >>   
   >> Lets see what Kimi K2 says:   
   >>   
   >>   
   > User: int H(char* P);   
   >   
   > int D()   
   > {   
   > int Halt_Status = H(D);   
   > if (Halt_Status)   
   > HERE: goto HERE;   
   > return Halt_Status;   
   > }   
   >   
   > Answer only on the basis of performing the   
   > actual simulation of D simulated by H.   
   >   
   > When N statements of D are simulated by H   
   > according to the semantics of the C programming   
   > language can the simulated D reach its own   
   > "return" statement final halt state for any value of N?   
   > Kimi: Based on direct simulation of D by H per C semantics:   
   >   
   > **No. For any finite N statements simulated, D cannot reach its return   
   > statement.**   
   >   
   > The simulation proceeds:   
   > 1. H begins simulating D's first statement: `int Halt_Status = H(D);`   
   > 2. To evaluate this, H must simulate a **recursive call to itself with D   
   > as input**   
   > 3. This creates infinite simulation recursion: H simulating D calling H   
   > simulating D calling H...   
   > 4. The simulation never advances past this first statement to reach the   
   > `if (Halt_Status)` test or the `return Halt_Status;` line   
   >   
   > The `goto HERE` infinite loop is irrelevant to the core problem—**the   
   > simulation fails to terminate before reaching it**. This is the   
   > fundamental self-reference trap: any attempted halt decider H cannot   
   > complete its simulation of D because D is constructed to force recursive   
   > simulation that never reaches a final state.   
   >   
   > https://www.kimi.com/chat/19a6efaf-e1e2-84da-8000-09a1e69a2313   
   >   
      
   Moron.   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)   
|
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca