Re: Even Google AI Overview understands me now --- different execution traces have different behavior !!!

On 10/3/24 10:48 PM, olcott wrote:

On 10/3/2024 8:17 PM, Richard Damon wrote:

On 10/3/24 6:46 PM, olcott wrote:

On 10/3/2024 6:16 AM, Richard Damon wrote:

On 10/2/24 10:09 PM, olcott wrote:

On 10/2/2024 5:48 PM, Richard Damon wrote:

On 10/2/24 10:39 AM, olcott wrote:

On 10/2/2024 6:08 AM, Richard Damon wrote:

On 10/1/24 7:26 PM, olcott wrote:

On 10/1/2024 12:58 PM, joes wrote:

Am Tue, 01 Oct 2024 12:31:41 -0500 schrieb olcott:

On 10/1/2024 8:09 AM, joes wrote:

Am Tue, 01 Oct 2024 07:39:18 -0500 schrieb olcott:

On 10/1/2024 7:19 AM, olcott wrote:

https://www.google.com/search?
>

>

q=Termination+Analyzer+H+is+Not+Fooled+by+Pathological+Input+D&sca_esv=889093c5cb21af9e&sca_upv=1&source=hp&ei=Muf7ZpOyMZHfwN4PwYL2gAc&iflsig=AL9hbdgAAAAAZvv1Qg04jNg2ze170z3a8BSGu8pA29Fj&ved=0ahUKEwiTk7zkk-2IAxWRL9AFHUGBHXAQ4dUDCBg&uact=5&oq=Termination+Analyzer+H+is+Not+Fooled+by+Pathological+Input+D&gs_lp=Egdnd3Mtd2l6IjxUZXJtaW5hdGlvbiBBbmFseXplciBIIGlzIE5vdCBGb29sZWQgYnkgUGF0aG9sb2dpY2FsIElucHV0IERIAFAAWABwAHgAkAEAmAEAoAEAqgEAuAEDyAEA-

AEC-AEBmAIAoAIAmAMAkgcAoAcA&sclient=gws-wiz

https://chatgpt.com/share/66fbec5c-7b10-8011-9ce6-3c26424cb21c

It sounds like it’s trained on your spam. LLMs don’t know anything
anyway.

>

I asked: „What happens when HHH tries to simulate itself?”
ChatGPT: [my comments in brackets]

>

### 1. **Self-Invocation in HHH**
If `HHH` calls itself (i.e., `HHH(HHH)`), it creates an infinite loop
of calls unless there is some form of termination condition built into
`HHH`.
Without such a condition, `HHH` would never return, resulting in non-
termination.
[So not a decider.]
>
### 2. **Halting Criteria**
In a well-designed termination analyzer, `HHH` would need to have
specific logic to prevent endless recursion:

>

[Not present.]
>
### 3. **Practical Consequences**
If `HHH` lacks the ability to handle self-referential calls correctly:
- **Stack Overflow**: Continuous self-invocation will eventually
exhaust the stack memory, leading to a stack overflow error.
[Not considered in theory.]
- **Incorrect Results**: If not designed carefully, it may lead to an
incorrect conclusion about halting, misrepresenting itself as either
halting or non-halting.
>
### 4. **Best Practices for Termination Analyzers**
To avoid these pitfalls, a termination analyzer should implement:
- **Guard Clauses**: Checks at the beginning of the function to prevent
unnecessary self-simulation.
- **State Management**: A way to track the functions being analyzed,
allowing `HHH` to recognize if it's being invoked with itself and act
accordingly.
>
### Conclusion In summary, if `HHH` tries to simulate itself without
proper safeguards,
it risks falling into an infinite recursion or causing a stack
overflow. A robust design would include checks to prevent
self-invocation, ensuring the termination analyzer can handle all
cases, including its own function,
gracefully.
>

*You can continue this conversation with ChatGPT*

I’ll leave that to you.

Click on the link and see how it answers this question:
Is H a Halt Decider for D?

You should feed it our objections.
If you believe in it only when you prompt it, it is not suited as an
authority (fallacious anyway).
>

>
You feed it your objections.
It will tell you how and why you are wrong.
>

>
No, it will tell you something that matches the words you told it.
>
You don't seem to understand what Large Language Models are.
>
>
You seem to forget that LLM know nothing of the "truth", only what matches their training data.
>
They are know to be liars, just like you.

>
In the case of their evaluation of my work they are correct.
>
*Try this yourself*
>
https://chatgpt.com/share/66fbec5c-7b10-8011-9ce6-3c26424cb21c
>
Does HHH have to abort its emulation of DDD to prevent the infinite execution of DDD?
>
>

>
Try asking it
>
Why is it ok for HHH to say that DDD doesn't halt when it will when run?
>

>
You guys try to pretend that the pathological relationship between
HHH and DDD does not make any difference to the behavior of DDD
knowing full well that it does make a difference.
>
When two execution traces differ and one expects the same behavior
this is the same as analogous to the insanity of doing the exact
same thing and expecting different results. It is merely the other
side. Doing an entirely different thing and expecting the same
results is also quite crazy.
>

>
No, YOU don't seem to understand that the while the pathological relationship DOES affect the behavior of DDD, it doesn't mean that the "correct simulation" of DDD (by anybody) will differ from the actual behavior of DDD.
>

>
If the emulator ignores rather than emulates this
pathological relationship when the x86 code specifies
this pathological relationship then it is the same
kind of damned liar that you are.
>

>
>
So, what did it actually EMULATE that differed?
>

 The directly executed DDD() depends on HHH aborting what
would otherwise be its own infinite recursive emulation.

So? Since that is what the code of that HHH does, that is what DDD does.
It seems you dopn't understand the meaning of the word "Program", or that you LIE that you are following the rules of the logic field the problem is from.
A Halt Decider (or Termination Analyser) takes as an in "A PROGRAM". given as a representation of it.
Being a program, this is, by definition, the entirety of the program, which includes the full defintion, (as programs) of every piece of code that it uses.
This include the code of the HHH that it calls.
Thus, HHH when it is reasoning about the behavior of DDD must include the fact that the HHH that it sees DDD calls is exactly the HHH that it actually calls, which *IS* the one that aborts and returns to it, even when HHH imagines itself hypothetically not aborting.
To do otherwise says that you are LIES about something, either that HHH took as an input the description of a PROGRAM, or that HHH has "correctly" determined the actual behavior of that progam, or that the actual behavior of the program is what HHH is even looking for.

 Mike is the only one smart enough to understand these things
and he refuses to, providing double-talk instead of reasoning.
  

You are just showing that:
PPPP   EEEEE  TTTTT  EEEEE  RRRR
P   P  E        T    E      R   R
P   P  E        T    E      R   R
PPPP   EEEEE    T    EEEEE  RRRR
P      E        T    E      R R
P      E        T    E      R  R
P      EEEEE    T    EEEEE  R   R
  OOO   L       CCC    OOO   TTTTT  TTTTT
O   O  L      C   C  O   O    T      T
O   O  L      C      O   O    T      T
O   O  L      C      O   O    T      T
O   O  L      C      O   O    T      T
O   O  L      C   C  O   O    T      T
  OOO   LLLLL   CCC    OOO     T      T
L     IIIII  EEEEE   SSS
L       I    E      S   S
L       I    E      S
L       I    EEEEE   SSS
L       I    E          S
L       I    E      S   S
LLLLL IIIII  EEEEE   SSS
AND THINKS THAT IS JUST OK.