Path: ...!weretis.net!feeder8.news.weretis.net!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail
From: olcott <polcott333@gmail.com>
Newsgroups: comp.theory
Subject: Re: Even Google AI Overview understands me now
Date: Tue, 1 Oct 2024 18:36:45 -0500
Organization: A noiseless patient Spider
Lines: 72
Message-ID: <vdi12d$2u3d2$1@dont-email.me>
References: <vdgpbs$2nmcm$1@dont-email.me> <vdgqhn$2nmcm$2@dont-email.me>
 <7c6cede5237e3eafee262c74dd1a1c90c6b2ffbb@i2pn2.org>
 <vdhblt$2qm1j$2@dont-email.me>
 <cafee8d7a14edd7b1d76bb706c36eef06ae82896@i2pn2.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Date: Wed, 02 Oct 2024 01:36:45 +0200 (CEST)
Injection-Info: dont-email.me; posting-host="ddfbe8e236b96e9eb22acbe29860ad61";
	logging-data="3083682"; mail-complaints-to="abuse@eternal-september.org";	posting-account="U2FsdGVkX1+tMcTYpa1ytt7WuvxGeBA9"
User-Agent: Mozilla Thunderbird
Cancel-Lock: sha1:Pr1/qLDsNJwDLqkR5vHpjlhlcMA=
In-Reply-To: <cafee8d7a14edd7b1d76bb706c36eef06ae82896@i2pn2.org>
Content-Language: en-US
Bytes: 4610

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).
> 

I did feed it your first objection: [So not a decider.]
By asking it: Is H a Halt Decider for D?
and it did explain exactly how you are wrong.

-- 
Copyright 2024 Olcott "Talent hits a target no one else can hit; Genius
hits a target no one else can see." Arthur Schopenhauer