Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > sci.physics.relativity > #667198 > unrolled thread

OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch)

Back to article view | Back to sci.physics.relativity

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) Mild Shock <janburse@fastmail.fm> - 2025-11-10 15:57 +0100
    Re: OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) olcott <polcott333@gmail.com> - 2025-11-10 12:20 -0600
      Re: OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2025-11-10 12:08 -0800
    Re: OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-11-10 17:05 -0800
    The joy of running an AI Model on your AI Laptop [Local AI] (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem]) Mild Shock <janburse@fastmail.fm> - 2025-11-11 21:09 +0100
    The joy of running an AI Model on your AI Laptop [Local AI] (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem]) Mild Shock <janburse@fastmail.fm> - 2025-11-11 21:12 +0100
      Cute Racoon generated with Local AI (Was: The joy of running an AI Model on your AI Laptop [Local AI]) Mild Shock <janburse@fastmail.fm> - 2025-11-11 23:26 +0100
    Meta is Dust: Yann LeCun crushed by Behemoth China (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem]) Mild Shock <janburse@fastmail.fm> - 2025-11-13 19:03 +0100
      Even Prolog now depends on China (Was: Meta is Dust: Yann LeCun crushed by Behemoth China) Mild Shock <janburse@fastmail.fm> - 2025-11-13 19:13 +0100
        Re: Even Prolog now depends on China (Was: Meta is Dust: Yann LeCun crushed by Behemoth China) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-11-13 11:42 -0800

#667198 — OpenAI is Toast: Kimi K2 is Live [Halting Problem] (Was: USA domestic chips for the never ending crunch)

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:

Q: In the arithmetic hierarchy counter models are
a level higher, than provability.

A: I think you're referring to a well-known fact
in logic: the set of (codes of) sentences that
are true in some model of arithmetic is one level
higher in the arithmetical hierarchy than the set
of sentences that are provable in, say, Peano Arithmetic.

Let me double-check the precise levels and any subtleties.
Let me bring in a classic reference that spells out the
exact levels. The key fact is:

The set of (Gödel numbers of) sentences provable in
Peano Arithmetic is recursively enumerable, hence Σ₁⁰.
The set of sentences that are true in some model of
PA is Σ₂⁰ (and complete for that level).

A concise statement of this can be found in Hinman’s
textbook or in the classic survey by Kreisel & Levy.
Let me look for an explicit citation.

Exactly — the blog post I just fetched already says
it in plain language:
“∃y (y Gödel-codes a proof from PA of the sentence Gödel-coded by x) … 
defines the set of natural numbers that encode theorems of PA. … This 
set is … Σ₁.”
So the set of provable sentences is Σ₁.
A couple of paragraphs later it continues:
“Σ₂ sets are those that can be defined by a sentence that
has a block of ∃s, then a block of ∀s, and finally
a Σ₀ sentence …
…
∃y ∀z (TM(x) doesn’t halt on input y after z steps)
… defines the set of Turing machines that compute partial functions.”
That set is Σ₂ and is not Σ₁.

Now let me connect the dots explicitly:
Provability = “there exists a proof” ⇒ one
unbounded ∃ ⇒ Σ₁.
Satisfiability (having a model) = “there exists a
model” followed by “for every axiom, it is true in
that model” ⇒ ∃ followed by ∀ ⇒ Σ₂.
Hence, as your couplet says, In the arithmetic hierarchy,
counter-models are a level higher than provability.

they indeed sit one step higher: Σ₂ vs. Σ₁.

Click the link to view conversation with Kimi AI Assistant 
https://www.kimi.com/share/19a6e410-3582-81e2-8000-00000e33bfe3

Bye

Mild Shock schrieb:
> Hi,
> 
> So the Tibetan lamasery had it right,
> the lights go out. There is a never ending
> hunger for crunch? Even requiring USA
> 
> to go into domestic chip production:
> 
> America’s Most Advanced Chip Factory Yet
> https://www.youtube.com/watch?v=1VX3jNJmbcI
> 
> But chip production etc.. (embodied energy) is
> only a fraction of the energy consumption:
> 
>  > Operational energy (running the data center
>  > for 1 year at 1 GW) = 8,760 TWh Hardware
>  > manufacturing energy = 0.75 TWh
>  > So the energy to produce the hardware is
>  > roughly 0.0085 (or 0.85%) of the annual
>  > operational energy.
> 
> What are the projections? By 2030, global
> power demand for data centers is projected to
> reach approximately 220 GW, underscoring the
> 
> urgency and strategic importance of securing
> power and hardware capacity:
> 
> $100B Bet on 10GW AI Infrastructure
> https://51ai.substack.com/p/openai-nvidia-100b-bet-on-10gw-ai
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Interestingly there is also now a top-ten
>> for AI data centers, not only super computers.
>> We are talking about newly built AI data centers
>>
>> that for the first time go into giga watts:
>>
>> The New World’s Largest AI Supercluster
>> https://www.youtube.com/watch?v=RxuSvyOwVCI
>>
>> Some confirmed picks:
>>
>> xAI Colossus Memphis
>> Phase 1    100000    xAI    U.S.    Confirmed
>> Tesla Cortex Phase 1    50000    Tesla    U.S.    Confirmed
>> Lawrence Livermore NL
>> El Capitan Phase 2    44143    U.S. Department of
>> Energy    U.S.    Confirmed
>> Anonymized Chinese
>> System    30000    N/A    China    Confirmed
>> Meta GenAI 2024a    24576    Meta AI    U.S.    Confirmed
>> Meta GenAI 2024b    24576    Meta AI    U.S.    Confirmed
>> Jupiter, Jülich    23536    EuroHPC JU,
>> Jülich Supercomputing
>> Center    Germany    Confirmed
>> Anonymized Chinese
>> System    20000    N/A    China    Confirmed
>> Anonymized Chinese
>> System    20000    N/A    China    Confirmed
>>
>> https://www.visualcapitalist.com/the-worlds-most-powerful-ai-supercomputers/ 
>>
>> Bye
>>
>> Mild Shock schrieb:
>>>
>>>
>>> In a Tibetan lamasery, the monks seek to
>>> list all of the names of God. They believe
>>> the Universe was created for this purpose,
>>> and that once this naming is completed, God
>>> will bring the Universe to an end. Three
>>>
>>> centuries ago, the monks created an alphabet
>>> in which they calculated they could encode
>>> all the possible names of God, numbering
>>> about 9,000,000,000 ("nine billion") and
>>> each having no more than nine characters.
>>>
>>> riting the names out by hand, as they had
>>> been doing, even after eliminating various
>>> nonsense combinations, would take another
>>> 15,000 years; the monks wish to use modern
>>> technology to finish this task in 100 days.
>>>
>>> They rent a computer capable of printing all
>>> the possible permutations, and hire two
>>> Westerners to install and program the machine.
>>> The computer operators are skeptical but
>>> play along. After three months, as the job
>>>
>>> nears completion, they fear that the monks
>>> will blame the computer (and, by extension,
>>> its operators) when nothing happens. The
>>> Westerners leave slightly earlier than their
>>> scheduled departure without warning the monks,
>>>
>>> so that it will complete its final print run
>>> shortly after they leave. On their way to the
>>> airfield they pause on the mountain path. Under
>>> a clear night sky they es timate that it must be
>>> just about the time that the monks are pasting
>>>
>>> the final printed names into their holy books.
>>> Then they notice that "overhead, without any
>>> fuss, the stars were going out."
>>>
>>> https://en.wikipedia.org/wiki/The_Nine_Billion_Names_of_God
>>
> 

[toc] | [next] | [standalone]

#667204

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

-- 
Copyright 2025 Olcott "Talent hits a target no one else can hit; Genius
hits a target no one else can see." Arthur Schopenhauer

[toc] | [prev] | [next] | [standalone]

#667206

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.

[toc] | [prev] | [next] | [standalone]

#667209

So, those are
your axioms of models
of axioms of models
of axioms of models
and so on, ....

Is it:  ad _infinitum_, or ad _absurdam_?

The difference is that ad _infinitum_
keeps the surds as forms reaching forms,
not forms not reaching forms.

So, infinitary reasoning re-introduces itself.


In the language of the language of
the language, and so on, ....


Since us realists are structuralists,
model theory itself evokes structure,
and it's quite thoroughly equi-interpretable
with proof theory, where proofs are discovered,
while descriptions arise as distinctness,
making it easy to be a conscientious
stronger mathematical platonist and
strong logicist positivist both.



Oh, so now I was right all along,
and you just couldn't or wouldn't see it,
and you think it's cute-sy to be cute-sy
instead of correct to be at all contrite?

I suppose that's better than nothing, ....

Yet, it still leaves all what you had there
as just wrong instead of correct(ed).

Either that, or you never said anything
at all.  Yet then your axioms would be false.

How about "Wow.  Thanks!"




On 11/10/2025 06:57 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:
>
> Q: In the arithmetic hierarchy counter models are
> a level higher, than provability.
>
> A: I think you're referring to a well-known fact
> in logic: the set of (codes of) sentences that
> are true in some model of arithmetic is one level
> higher in the arithmetical hierarchy than the set
> of sentences that are provable in, say, Peano Arithmetic.
>
> Let me double-check the precise levels and any subtleties.
> Let me bring in a classic reference that spells out the
> exact levels. The key fact is:
>
> The set of (Gödel numbers of) sentences provable in
> Peano Arithmetic is recursively enumerable, hence Σ₁⁰.
> The set of sentences that are true in some model of
> PA is Σ₂⁰ (and complete for that level).
>
> A concise statement of this can be found in Hinman’s
> textbook or in the classic survey by Kreisel & Levy.
> Let me look for an explicit citation.
>
> Exactly — the blog post I just fetched already says
> it in plain language:
> “∃y (y Gödel-codes a proof from PA of the sentence Gödel-coded by x) …
> defines the set of natural numbers that encode theorems of PA. … This
> set is … Σ₁.”
> So the set of provable sentences is Σ₁.
> A couple of paragraphs later it continues:
> “Σ₂ sets are those that can be defined by a sentence that
> has a block of ∃s, then a block of ∀s, and finally
> a Σ₀ sentence …
> …
> ∃y ∀z (TM(x) doesn’t halt on input y after z steps)
> … defines the set of Turing machines that compute partial functions.”
> That set is Σ₂ and is not Σ₁.
>
> Now let me connect the dots explicitly:
> Provability = “there exists a proof” ⇒ one
> unbounded ∃ ⇒ Σ₁.
> Satisfiability (having a model) = “there exists a
> model” followed by “for every axiom, it is true in
> that model” ⇒ ∃ followed by ∀ ⇒ Σ₂.
> Hence, as your couplet says, In the arithmetic hierarchy,
> counter-models are a level higher than provability.
>
> they indeed sit one step higher: Σ₂ vs. Σ₁.
>
> Click the link to view conversation with Kimi AI Assistant
> https://www.kimi.com/share/19a6e410-3582-81e2-8000-00000e33bfe3
>
> Bye
>
> Mild Shock schrieb:
>> Hi,
>>
>> So the Tibetan lamasery had it right,
>> the lights go out. There is a never ending
>> hunger for crunch? Even requiring USA
>>
>> to go into domestic chip production:
>>
>> America’s Most Advanced Chip Factory Yet
>> https://www.youtube.com/watch?v=1VX3jNJmbcI
>>
>> But chip production etc.. (embodied energy) is
>> only a fraction of the energy consumption:
>>
>>  > Operational energy (running the data center
>>  > for 1 year at 1 GW) = 8,760 TWh Hardware
>>  > manufacturing energy = 0.75 TWh
>>  > So the energy to produce the hardware is
>>  > roughly 0.0085 (or 0.85%) of the annual
>>  > operational energy.
>>
>> What are the projections? By 2030, global
>> power demand for data centers is projected to
>> reach approximately 220 GW, underscoring the
>>
>> urgency and strategic importance of securing
>> power and hardware capacity:
>>
>> $100B Bet on 10GW AI Infrastructure
>> https://51ai.substack.com/p/openai-nvidia-100b-bet-on-10gw-ai
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Interestingly there is also now a top-ten
>>> for AI data centers, not only super computers.
>>> We are talking about newly built AI data centers
>>>
>>> that for the first time go into giga watts:
>>>
>>> The New World’s Largest AI Supercluster
>>> https://www.youtube.com/watch?v=RxuSvyOwVCI
>>>
>>> Some confirmed picks:
>>>
>>> xAI Colossus Memphis
>>> Phase 1    100000    xAI    U.S.    Confirmed
>>> Tesla Cortex Phase 1    50000    Tesla    U.S.    Confirmed
>>> Lawrence Livermore NL
>>> El Capitan Phase 2    44143    U.S. Department of
>>> Energy    U.S.    Confirmed
>>> Anonymized Chinese
>>> System    30000    N/A    China    Confirmed
>>> Meta GenAI 2024a    24576    Meta AI    U.S.    Confirmed
>>> Meta GenAI 2024b    24576    Meta AI    U.S.    Confirmed
>>> Jupiter, Jülich    23536    EuroHPC JU,
>>> Jülich Supercomputing
>>> Center    Germany    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>>
>>> https://www.visualcapitalist.com/the-worlds-most-powerful-ai-supercomputers/
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>>
>>>>
>>>> In a Tibetan lamasery, the monks seek to
>>>> list all of the names of God. They believe
>>>> the Universe was created for this purpose,
>>>> and that once this naming is completed, God
>>>> will bring the Universe to an end. Three
>>>>
>>>> centuries ago, the monks created an alphabet
>>>> in which they calculated they could encode
>>>> all the possible names of God, numbering
>>>> about 9,000,000,000 ("nine billion") and
>>>> each having no more than nine characters.
>>>>
>>>> riting the names out by hand, as they had
>>>> been doing, even after eliminating various
>>>> nonsense combinations, would take another
>>>> 15,000 years; the monks wish to use modern
>>>> technology to finish this task in 100 days.
>>>>
>>>> They rent a computer capable of printing all
>>>> the possible permutations, and hire two
>>>> Westerners to install and program the machine.
>>>> The computer operators are skeptical but
>>>> play along. After three months, as the job
>>>>
>>>> nears completion, they fear that the monks
>>>> will blame the computer (and, by extension,
>>>> its operators) when nothing happens. The
>>>> Westerners leave slightly earlier than their
>>>> scheduled departure without warning the monks,
>>>>
>>>> so that it will complete its final print run
>>>> shortly after they leave. On their way to the
>>>> airfield they pause on the mountain path. Under
>>>> a clear night sky they es timate that it must be
>>>> just about the time that the monks are pasting
>>>>
>>>> the final printed names into their holy books.
>>>> Then they notice that "overhead, without any
>>>> fuss, the stars were going out."
>>>>
>>>> https://en.wikipedia.org/wiki/The_Nine_Billion_Names_of_God
>>>
>>
>

[toc] | [prev] | [next] | [standalone]

#667219 — The joy of running an AI Model on your AI Laptop [Local AI] (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem])

Hi,

Now that was a little unexpected that Intel beats AMD.
Could get my hands on two AI Laptops for testing.
The have both DDR5X Ram.

AI Laptop 1: Acer_Swift_SFG16-61
AMD Ryzen 7 350
Radeon Graphics
AMD Ryzen AI Boost, up to 50 TOPS

AI Laptop 2: LENOVO_83JQ
Intel Core Ultra 7 258V
Intel Arc Graphics 140V
Intel AI Boost, up to 47 TOPS

I couldn't test the AI Boost yet. Besides the nice
CPUs, the iGPU and the fast memory, in this case
32 GB, seem to give quite some bang:

Here some test with LMStudio, I picked the
model Qwen3 Coder 30B, with Q4_K_M encoding,
which is around 16 GB, and fits into my GPU memory:
https://lmstudio.ai/models/qwen/qwen3-coder-30b

AI Laptop 1: 18 Tokens/s

AI Laptop 2: 6 Tokens/s

Now I am waiting for drivers and applications
that make use of the AI Boost. Will say
I only tested the iGPU, not yet the NPU.

For the donwload of the AI model it is
required to have fiber and WiFi 6, you can
then make it in less than a minute, even

if you are far away from the router.

Bye

P.S.: The 18 Tokens/s are quite fluid,
the 6 Tokens/s are a little annoying. But
on both machines I could converse with the

model, and go from primes to twin primes.
It didn't use any RAG, fully produce via
Local AI, also remote AI access after

download of the AI Model:

----------------- cut here ---------------------

Here's a Prolog implementation to find
twin prime pairs (pairs of primes that differ by 2):

% Generate twin prime pairs up to N
twin_primes_up_to(N, TwinPairs) :-
     findall((P, Q),
             (between(3, N, P),
              is_prime(P),
              Q is P + 2,
              is_prime(Q)),
             TwinPairs).

% Check if a number is prime
is_prime(2) :- !.
is_prime(3) :- !.
is_prime(N) :-
     N > 3,
     N mod 2 =\= 0,          % Even numbers > 2 are not prime
     \+ has_factor(N, 3).    % Check if N has any factors starting from 3

% Check if N has a factor starting from F
has_factor(N, F) :-
     F * F =< N,
     (N mod F =:= 0 ; has_factor(N, F + 2)).

Example usage:

?- twin_primes_up_to(20, Pairs).
Pairs = [(3, 5), (5, 7), (11, 13), (17, 19)].

?- twin_primes_up_to(50, Pairs).
Pairs = [(3, 5), (5, 7), (11, 13), (17, 19), (29, 31), (41, 43)].

This finds pairs of primes (P, Q) where Q = P + 2,
which are called twin primes. The findall/3 predicate
collects all such pairs where both P and P+2 are
prime numbers and P is less than or equal to N.

----------------- cut here ---------------------

Mild Shock schrieb:
> 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:
> 
> Q: In the arithmetic hierarchy counter models are
> a level higher, than provability.
> 
> A: I think you're referring to a well-known fact
> in logic: the set of (codes of) sentences that
> are true in some model of arithmetic is one level
> higher in the arithmetical hierarchy than the set
> of sentences that are provable in, say, Peano Arithmetic.
> 
> Let me double-check the precise levels and any subtleties.
> Let me bring in a classic reference that spells out the
> exact levels. The key fact is:
> 
> The set of (Gödel numbers of) sentences provable in
> Peano Arithmetic is recursively enumerable, hence Σ₁⁰.
> The set of sentences that are true in some model of
> PA is Σ₂⁰ (and complete for that level).
> 
> A concise statement of this can be found in Hinman’s
> textbook or in the classic survey by Kreisel & Levy.
> Let me look for an explicit citation.
> 
> Exactly — the blog post I just fetched already says
> it in plain language:
> “∃y (y Gödel-codes a proof from PA of the sentence Gödel-coded by x) … 
> defines the set of natural numbers that encode theorems of PA. … This 
> set is … Σ₁.”
> So the set of provable sentences is Σ₁.
> A couple of paragraphs later it continues:
> “Σ₂ sets are those that can be defined by a sentence that
> has a block of ∃s, then a block of ∀s, and finally
> a Σ₀ sentence …
> …
> ∃y ∀z (TM(x) doesn’t halt on input y after z steps)
> … defines the set of Turing machines that compute partial functions.”
> That set is Σ₂ and is not Σ₁.
> 
> Now let me connect the dots explicitly:
> Provability = “there exists a proof” ⇒ one
> unbounded ∃ ⇒ Σ₁.
> Satisfiability (having a model) = “there exists a
> model” followed by “for every axiom, it is true in
> that model” ⇒ ∃ followed by ∀ ⇒ Σ₂.
> Hence, as your couplet says, In the arithmetic hierarchy,
> counter-models are a level higher than provability.
> 
> they indeed sit one step higher: Σ₂ vs. Σ₁.
> 
> Click the link to view conversation with Kimi AI Assistant 
> https://www.kimi.com/share/19a6e410-3582-81e2-8000-00000e33bfe3
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> So the Tibetan lamasery had it right,
>> the lights go out. There is a never ending
>> hunger for crunch? Even requiring USA
>>
>> to go into domestic chip production:
>>
>> America’s Most Advanced Chip Factory Yet
>> https://www.youtube.com/watch?v=1VX3jNJmbcI
>>
>> But chip production etc.. (embodied energy) is
>> only a fraction of the energy consumption:
>>
>>  > Operational energy (running the data center
>>  > for 1 year at 1 GW) = 8,760 TWh Hardware
>>  > manufacturing energy = 0.75 TWh
>>  > So the energy to produce the hardware is
>>  > roughly 0.0085 (or 0.85%) of the annual
>>  > operational energy.
>>
>> What are the projections? By 2030, global
>> power demand for data centers is projected to
>> reach approximately 220 GW, underscoring the
>>
>> urgency and strategic importance of securing
>> power and hardware capacity:
>>
>> $100B Bet on 10GW AI Infrastructure
>> https://51ai.substack.com/p/openai-nvidia-100b-bet-on-10gw-ai
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Interestingly there is also now a top-ten
>>> for AI data centers, not only super computers.
>>> We are talking about newly built AI data centers
>>>
>>> that for the first time go into giga watts:
>>>
>>> The New World’s Largest AI Supercluster
>>> https://www.youtube.com/watch?v=RxuSvyOwVCI
>>>
>>> Some confirmed picks:
>>>
>>> xAI Colossus Memphis
>>> Phase 1    100000    xAI    U.S.    Confirmed
>>> Tesla Cortex Phase 1    50000    Tesla    U.S.    Confirmed
>>> Lawrence Livermore NL
>>> El Capitan Phase 2    44143    U.S. Department of
>>> Energy    U.S.    Confirmed
>>> Anonymized Chinese
>>> System    30000    N/A    China    Confirmed
>>> Meta GenAI 2024a    24576    Meta AI    U.S.    Confirmed
>>> Meta GenAI 2024b    24576    Meta AI    U.S.    Confirmed
>>> Jupiter, Jülich    23536    EuroHPC JU,
>>> Jülich Supercomputing
>>> Center    Germany    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>>
>>> https://www.visualcapitalist.com/the-worlds-most-powerful-ai-supercomputers/ 
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>>
>>>>
>>>> In a Tibetan lamasery, the monks seek to
>>>> list all of the names of God. They believe
>>>> the Universe was created for this purpose,
>>>> and that once this naming is completed, God
>>>> will bring the Universe to an end. Three
>>>>
>>>> centuries ago, the monks created an alphabet
>>>> in which they calculated they could encode
>>>> all the possible names of God, numbering
>>>> about 9,000,000,000 ("nine billion") and
>>>> each having no more than nine characters.
>>>>
>>>> riting the names out by hand, as they had
>>>> been doing, even after eliminating various
>>>> nonsense combinations, would take another
>>>> 15,000 years; the monks wish to use modern
>>>> technology to finish this task in 100 days.
>>>>
>>>> They rent a computer capable of printing all
>>>> the possible permutations, and hire two
>>>> Westerners to install and program the machine.
>>>> The computer operators are skeptical but
>>>> play along. After three months, as the job
>>>>
>>>> nears completion, they fear that the monks
>>>> will blame the computer (and, by extension,
>>>> its operators) when nothing happens. The
>>>> Westerners leave slightly earlier than their
>>>> scheduled departure without warning the monks,
>>>>
>>>> so that it will complete its final print run
>>>> shortly after they leave. On their way to the
>>>> airfield they pause on the mountain path. Under
>>>> a clear night sky they es timate that it must be
>>>> just about the time that the monks are pasting
>>>>
>>>> the final printed names into their holy books.
>>>> Then they notice that "overhead, without any
>>>> fuss, the stars were going out."
>>>>
>>>> https://en.wikipedia.org/wiki/The_Nine_Billion_Names_of_God
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]

#667220 — The joy of running an AI Model on your AI Laptop [Local AI] (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem])

Hi,

Now that was a little unexpected that Intel beats AMD.
Could get my hands on two AI Laptops for testing.
The have both DDR5X Ram.

AI Laptop 1: Acer_Swift_SFG16-61
AMD Ryzen 7 350
Radeon Graphics
AMD Ryzen AI Boost, up to 50 TOPS

AI Laptop 2: LENOVO_83JQ
Intel Core Ultra 7 258V
Intel Arc Graphics 140V
Intel AI Boost, up to 47 TOPS

I couldn't test the AI Boost yet. Besides the nice
CPUs, the iGPU and the fast memory, in this case
32 GB, seem to give quite some bang:

Here some test with LMStudio, I picked the
model Qwen3 Coder 30B, with Q4_K_M encoding,
which is around 16 GB, and fits into my GPU memory:
https://lmstudio.ai/models/qwen/qwen3-coder-30b

AI Laptop 1: 18 Tokens/s

AI Laptop 2: 6 Tokens/s

Now I am waiting for drivers and applications
that make use of the AI Boost. Will say
I only tested the iGPU, not yet the NPU.

For the donwload of the AI model it is
required to have fiber and WiFi 6, you can
then make it in less than a minute, even

if you are far away from the router.

Bye

P.S.: The 18 Tokens/s are quite fluid,
the 6 Tokens/s are a little annoying. But
on both machines I could converse with the

model, and go from primes to twin primes.
It didn't use any RAG, fully produce via
Local AI, also no remote AI access after

download of the AI Model:

----------------- cut here ---------------------

Here's a Prolog implementation to find
twin prime pairs (pairs of primes that differ by 2):

% Generate twin prime pairs up to N
twin_primes_up_to(N, TwinPairs) :-
     findall((P, Q),
             (between(3, N, P),
              is_prime(P),
              Q is P + 2,
              is_prime(Q)),
             TwinPairs).

% Check if a number is prime
is_prime(2) :- !.
is_prime(3) :- !.
is_prime(N) :-
     N > 3,
     N mod 2 =\= 0,          % Even numbers > 2 are not prime
     \+ has_factor(N, 3).    % Check if N has any factors starting from 3

% Check if N has a factor starting from F
has_factor(N, F) :-
     F * F =< N,
     (N mod F =:= 0 ; has_factor(N, F + 2)).

Example usage:

?- twin_primes_up_to(20, Pairs).
Pairs = [(3, 5), (5, 7), (11, 13), (17, 19)].

?- twin_primes_up_to(50, Pairs).
Pairs = [(3, 5), (5, 7), (11, 13), (17, 19), (29, 31), (41, 43)].

This finds pairs of primes (P, Q) where Q = P + 2,
which are called twin primes. The findall/3 predicate
collects all such pairs where both P and P+2 are
prime numbers and P is less than or equal to N.

----------------- cut here ---------------------

Mild Shock schrieb:
> 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:
> 
> Q: In the arithmetic hierarchy counter models are
> a level higher, than provability.
> 
> A: I think you're referring to a well-known fact
> in logic: the set of (codes of) sentences that
> are true in some model of arithmetic is one level
> higher in the arithmetical hierarchy than the set
> of sentences that are provable in, say, Peano Arithmetic.
> 
> Let me double-check the precise levels and any subtleties.
> Let me bring in a classic reference that spells out the
> exact levels. The key fact is:
> 
> The set of (Gödel numbers of) sentences provable in
> Peano Arithmetic is recursively enumerable, hence Σ₁⁰.
> The set of sentences that are true in some model of
> PA is Σ₂⁰ (and complete for that level).
> 
> A concise statement of this can be found in Hinman’s
> textbook or in the classic survey by Kreisel & Levy.
> Let me look for an explicit citation.
> 
> Exactly — the blog post I just fetched already says
> it in plain language:
> “∃y (y Gödel-codes a proof from PA of the sentence Gödel-coded by x) … 
> defines the set of natural numbers that encode theorems of PA. … This 
> set is … Σ₁.”
> So the set of provable sentences is Σ₁.
> A couple of paragraphs later it continues:
> “Σ₂ sets are those that can be defined by a sentence that
> has a block of ∃s, then a block of ∀s, and finally
> a Σ₀ sentence …
> …
> ∃y ∀z (TM(x) doesn’t halt on input y after z steps)
> … defines the set of Turing machines that compute partial functions.”
> That set is Σ₂ and is not Σ₁.
> 
> Now let me connect the dots explicitly:
> Provability = “there exists a proof” ⇒ one
> unbounded ∃ ⇒ Σ₁.
> Satisfiability (having a model) = “there exists a
> model” followed by “for every axiom, it is true in
> that model” ⇒ ∃ followed by ∀ ⇒ Σ₂.
> Hence, as your couplet says, In the arithmetic hierarchy,
> counter-models are a level higher than provability.
> 
> they indeed sit one step higher: Σ₂ vs. Σ₁.
> 
> Click the link to view conversation with Kimi AI Assistant 
> https://www.kimi.com/share/19a6e410-3582-81e2-8000-00000e33bfe3
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> So the Tibetan lamasery had it right,
>> the lights go out. There is a never ending
>> hunger for crunch? Even requiring USA
>>
>> to go into domestic chip production:
>>
>> America’s Most Advanced Chip Factory Yet
>> https://www.youtube.com/watch?v=1VX3jNJmbcI
>>
>> But chip production etc.. (embodied energy) is
>> only a fraction of the energy consumption:
>>
>>  > Operational energy (running the data center
>>  > for 1 year at 1 GW) = 8,760 TWh Hardware
>>  > manufacturing energy = 0.75 TWh
>>  > So the energy to produce the hardware is
>>  > roughly 0.0085 (or 0.85%) of the annual
>>  > operational energy.
>>
>> What are the projections? By 2030, global
>> power demand for data centers is projected to
>> reach approximately 220 GW, underscoring the
>>
>> urgency and strategic importance of securing
>> power and hardware capacity:
>>
>> $100B Bet on 10GW AI Infrastructure
>> https://51ai.substack.com/p/openai-nvidia-100b-bet-on-10gw-ai
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Interestingly there is also now a top-ten
>>> for AI data centers, not only super computers.
>>> We are talking about newly built AI data centers
>>>
>>> that for the first time go into giga watts:
>>>
>>> The New World’s Largest AI Supercluster
>>> https://www.youtube.com/watch?v=RxuSvyOwVCI
>>>
>>> Some confirmed picks:
>>>
>>> xAI Colossus Memphis
>>> Phase 1    100000    xAI    U.S.    Confirmed
>>> Tesla Cortex Phase 1    50000    Tesla    U.S.    Confirmed
>>> Lawrence Livermore NL
>>> El Capitan Phase 2    44143    U.S. Department of
>>> Energy    U.S.    Confirmed
>>> Anonymized Chinese
>>> System    30000    N/A    China    Confirmed
>>> Meta GenAI 2024a    24576    Meta AI    U.S.    Confirmed
>>> Meta GenAI 2024b    24576    Meta AI    U.S.    Confirmed
>>> Jupiter, Jülich    23536    EuroHPC JU,
>>> Jülich Supercomputing
>>> Center    Germany    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>>
>>> https://www.visualcapitalist.com/the-worlds-most-powerful-ai-supercomputers/ 
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>>
>>>>
>>>> In a Tibetan lamasery, the monks seek to
>>>> list all of the names of God. They believe
>>>> the Universe was created for this purpose,
>>>> and that once this naming is completed, God
>>>> will bring the Universe to an end. Three
>>>>
>>>> centuries ago, the monks created an alphabet
>>>> in which they calculated they could encode
>>>> all the possible names of God, numbering
>>>> about 9,000,000,000 ("nine billion") and
>>>> each having no more than nine characters.
>>>>
>>>> riting the names out by hand, as they had
>>>> been doing, even after eliminating various
>>>> nonsense combinations, would take another
>>>> 15,000 years; the monks wish to use modern
>>>> technology to finish this task in 100 days.
>>>>
>>>> They rent a computer capable of printing all
>>>> the possible permutations, and hire two
>>>> Westerners to install and program the machine.
>>>> The computer operators are skeptical but
>>>> play along. After three months, as the job
>>>>
>>>> nears completion, they fear that the monks
>>>> will blame the computer (and, by extension,
>>>> its operators) when nothing happens. The
>>>> Westerners leave slightly earlier than their
>>>> scheduled departure without warning the monks,
>>>>
>>>> so that it will complete its final print run
>>>> shortly after they leave. On their way to the
>>>> airfield they pause on the mountain path. Under
>>>> a clear night sky they es timate that it must be
>>>> just about the time that the monks are pasting
>>>>
>>>> the final printed names into their holy books.
>>>> Then they notice that "overhead, without any
>>>> fuss, the stars were going out."
>>>>
>>>> https://en.wikipedia.org/wiki/The_Nine_Billion_Names_of_God
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]

#667222 — Cute Racoon generated with Local AI (Was: The joy of running an AI Model on your AI Laptop [Local AI])

Hi,

There is even more joy of running an AI Model
on your AI Laptop. All you need to put "AI Slob"
into the wild is Stable Diffusion Software and Models.

Cute Racoon generated with Local AI
https://www.youtube.com/shorts/QlS0MqMh_bM

Have Fun!

Bye

P.S.: Was using this gadget:

Create AI art, with the latest Stable
Diffusion models, on your own PC.
https://www.amuse-ai.com/

Mild Shock schrieb:
> Hi,
> 
> Now that was a little unexpected that Intel beats AMD.
> Could get my hands on two AI Laptops for testing.
> The have both DDR5X Ram.
> 
> AI Laptop 1: Acer_Swift_SFG16-61
> AMD Ryzen 7 350
> Radeon Graphics
> AMD Ryzen AI Boost, up to 50 TOPS
> 
> AI Laptop 2: LENOVO_83JQ
> Intel Core Ultra 7 258V
> Intel Arc Graphics 140V
> Intel AI Boost, up to 47 TOPS
> 
> I couldn't test the AI Boost yet. Besides the nice
> CPUs, the iGPU and the fast memory, in this case
> 32 GB, seem to give quite some bang:
> 
> Here some test with LMStudio, I picked the
> model Qwen3 Coder 30B, with Q4_K_M encoding,
> which is around 16 GB, and fits into my GPU memory:
> https://lmstudio.ai/models/qwen/qwen3-coder-30b
> 
> AI Laptop 1: 18 Tokens/s
> 
> AI Laptop 2: 6 Tokens/s
> 
> Now I am waiting for drivers and applications
> that make use of the AI Boost. Will say
> I only tested the iGPU, not yet the NPU.
> 
> For the donwload of the AI model it is
> required to have fiber and WiFi 6, you can
> then make it in less than a minute, even
> 
> if you are far away from the router.
> 
> Bye
> 
> P.S.: The 18 Tokens/s are quite fluid,
> the 6 Tokens/s are a little annoying. But
> on both machines I could converse with the
> 
> model, and go from primes to twin primes.
> It didn't use any RAG, fully produce via
> Local AI, also no remote AI access after
> 
> download of the AI Model:
> 
> ----------------- cut here ---------------------
> 
> Here's a Prolog implementation to find
> twin prime pairs (pairs of primes that differ by 2):
> 
> % Generate twin prime pairs up to N
> twin_primes_up_to(N, TwinPairs) :-
>      findall((P, Q),
>              (between(3, N, P),
>               is_prime(P),
>               Q is P + 2,
>               is_prime(Q)),
>              TwinPairs).
> 
> % Check if a number is prime
> is_prime(2) :- !.
> is_prime(3) :- !.
> is_prime(N) :-
>      N > 3,
>      N mod 2 =\= 0,          % Even numbers > 2 are not prime
>      \+ has_factor(N, 3).    % Check if N has any factors starting from 3
> 
> % Check if N has a factor starting from F
> has_factor(N, F) :-
>      F * F =< N,
>      (N mod F =:= 0 ; has_factor(N, F + 2)).
> 
> Example usage:
> 
> ?- twin_primes_up_to(20, Pairs).
> Pairs = [(3, 5), (5, 7), (11, 13), (17, 19)].
> 
> ?- twin_primes_up_to(50, Pairs).
> Pairs = [(3, 5), (5, 7), (11, 13), (17, 19), (29, 31), (41, 43)].
> 
> This finds pairs of primes (P, Q) where Q = P + 2,
> which are called twin primes. The findall/3 predicate
> collects all such pairs where both P and P+2 are
> prime numbers and P is less than or equal to N.
> 
> ----------------- cut here ---------------------

[toc] | [prev] | [next] | [standalone]

#667269 — Meta is Dust: Yann LeCun crushed by Behemoth China (Was: OpenAI is Toast: Kimi K2 is Live [Halting Problem])

Hi,

How it started:

RIP Deepseek. We have a new #1 open-source AI model
https://www.youtube.com/watch?v=xt6_zIKeX6A

How its going:

Meta’s AI Genius Just Quit — Even Zuckerberg Seems Surprised.
https://www.youtube.com/watch?v=W2tr1Q3D1ZI

I guess Yann LeCun was not paying attention
to the transition of LLM (Large Language Models)
to LRM (Large Reasoning Models).

Bye

Mild Shock schrieb:
> 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:
> 
> Q: In the arithmetic hierarchy counter models are
> a level higher, than provability.
> 
> A: I think you're referring to a well-known fact
> in logic: the set of (codes of) sentences that
> are true in some model of arithmetic is one level
> higher in the arithmetical hierarchy than the set
> of sentences that are provable in, say, Peano Arithmetic.
> 
> Let me double-check the precise levels and any subtleties.
> Let me bring in a classic reference that spells out the
> exact levels. The key fact is:
> 
> The set of (Gödel numbers of) sentences provable in
> Peano Arithmetic is recursively enumerable, hence Σ₁⁰.
> The set of sentences that are true in some model of
> PA is Σ₂⁰ (and complete for that level).
> 
> A concise statement of this can be found in Hinman’s
> textbook or in the classic survey by Kreisel & Levy.
> Let me look for an explicit citation.
> 
> Exactly — the blog post I just fetched already says
> it in plain language:
> “∃y (y Gödel-codes a proof from PA of the sentence Gödel-coded by x) … 
> defines the set of natural numbers that encode theorems of PA. … This 
> set is … Σ₁.”
> So the set of provable sentences is Σ₁.
> A couple of paragraphs later it continues:
> “Σ₂ sets are those that can be defined by a sentence that
> has a block of ∃s, then a block of ∀s, and finally
> a Σ₀ sentence …
> …
> ∃y ∀z (TM(x) doesn’t halt on input y after z steps)
> … defines the set of Turing machines that compute partial functions.”
> That set is Σ₂ and is not Σ₁.
> 
> Now let me connect the dots explicitly:
> Provability = “there exists a proof” ⇒ one
> unbounded ∃ ⇒ Σ₁.
> Satisfiability (having a model) = “there exists a
> model” followed by “for every axiom, it is true in
> that model” ⇒ ∃ followed by ∀ ⇒ Σ₂.
> Hence, as your couplet says, In the arithmetic hierarchy,
> counter-models are a level higher than provability.
> 
> they indeed sit one step higher: Σ₂ vs. Σ₁.
> 
> Click the link to view conversation with Kimi AI Assistant 
> https://www.kimi.com/share/19a6e410-3582-81e2-8000-00000e33bfe3
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> So the Tibetan lamasery had it right,
>> the lights go out. There is a never ending
>> hunger for crunch? Even requiring USA
>>
>> to go into domestic chip production:
>>
>> America’s Most Advanced Chip Factory Yet
>> https://www.youtube.com/watch?v=1VX3jNJmbcI
>>
>> But chip production etc.. (embodied energy) is
>> only a fraction of the energy consumption:
>>
>>  > Operational energy (running the data center
>>  > for 1 year at 1 GW) = 8,760 TWh Hardware
>>  > manufacturing energy = 0.75 TWh
>>  > So the energy to produce the hardware is
>>  > roughly 0.0085 (or 0.85%) of the annual
>>  > operational energy.
>>
>> What are the projections? By 2030, global
>> power demand for data centers is projected to
>> reach approximately 220 GW, underscoring the
>>
>> urgency and strategic importance of securing
>> power and hardware capacity:
>>
>> $100B Bet on 10GW AI Infrastructure
>> https://51ai.substack.com/p/openai-nvidia-100b-bet-on-10gw-ai
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Interestingly there is also now a top-ten
>>> for AI data centers, not only super computers.
>>> We are talking about newly built AI data centers
>>>
>>> that for the first time go into giga watts:
>>>
>>> The New World’s Largest AI Supercluster
>>> https://www.youtube.com/watch?v=RxuSvyOwVCI
>>>
>>> Some confirmed picks:
>>>
>>> xAI Colossus Memphis
>>> Phase 1    100000    xAI    U.S.    Confirmed
>>> Tesla Cortex Phase 1    50000    Tesla    U.S.    Confirmed
>>> Lawrence Livermore NL
>>> El Capitan Phase 2    44143    U.S. Department of
>>> Energy    U.S.    Confirmed
>>> Anonymized Chinese
>>> System    30000    N/A    China    Confirmed
>>> Meta GenAI 2024a    24576    Meta AI    U.S.    Confirmed
>>> Meta GenAI 2024b    24576    Meta AI    U.S.    Confirmed
>>> Jupiter, Jülich    23536    EuroHPC JU,
>>> Jülich Supercomputing
>>> Center    Germany    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>> Anonymized Chinese
>>> System    20000    N/A    China    Confirmed
>>>
>>> https://www.visualcapitalist.com/the-worlds-most-powerful-ai-supercomputers/ 
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>>
>>>>
>>>> In a Tibetan lamasery, the monks seek to
>>>> list all of the names of God. They believe
>>>> the Universe was created for this purpose,
>>>> and that once this naming is completed, God
>>>> will bring the Universe to an end. Three
>>>>
>>>> centuries ago, the monks created an alphabet
>>>> in which they calculated they could encode
>>>> all the possible names of God, numbering
>>>> about 9,000,000,000 ("nine billion") and
>>>> each having no more than nine characters.
>>>>
>>>> riting the names out by hand, as they had
>>>> been doing, even after eliminating various
>>>> nonsense combinations, would take another
>>>> 15,000 years; the monks wish to use modern
>>>> technology to finish this task in 100 days.
>>>>
>>>> They rent a computer capable of printing all
>>>> the possible permutations, and hire two
>>>> Westerners to install and program the machine.
>>>> The computer operators are skeptical but
>>>> play along. After three months, as the job
>>>>
>>>> nears completion, they fear that the monks
>>>> will blame the computer (and, by extension,
>>>> its operators) when nothing happens. The
>>>> Westerners leave slightly earlier than their
>>>> scheduled departure without warning the monks,
>>>>
>>>> so that it will complete its final print run
>>>> shortly after they leave. On their way to the
>>>> airfield they pause on the mountain path. Under
>>>> a clear night sky they es timate that it must be
>>>> just about the time that the monks are pasting
>>>>
>>>> the final printed names into their holy books.
>>>> Then they notice that "overhead, without any
>>>> fuss, the stars were going out."
>>>>
>>>> https://en.wikipedia.org/wiki/The_Nine_Billion_Names_of_God
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]

#667270 — Even Prolog now depends on China (Was: Meta is Dust: Yann LeCun crushed by Behemoth China)

Hi,

Because the Prolog community has dummbed itself
down over the last years. You don't find something
mildly interesting published by Prologers.

On the other hand Behemoth China has easy game:

8x Authors China:

Abductive Logical Rule Induction by Bridging Inductive
Logic Programming and Multimodal Large Language Models
https://arxiv.org/pdf/2509.21874

2x Authors China:

Domain-Contextualized Concept Graphs:
A Computable Framework for Knowledge Representation
https://arxiv.org/abs/2510.16802

Have Fun!

Bye

Mild Shock schrieb:
> Hi,
> 
> How it started:
> 
> RIP Deepseek. We have a new #1 open-source AI model
> https://www.youtube.com/watch?v=xt6_zIKeX6A
> 
> How its going:
> 
> Meta’s AI Genius Just Quit — Even Zuckerberg Seems Surprised.
> https://www.youtube.com/watch?v=W2tr1Q3D1ZI
> 
> I guess Yann LeCun was not paying attention
> to the transition of LLM (Large Language Models)
> to LRM (Large Reasoning Models).
> 
> Bye

[toc] | [prev] | [next] | [standalone]

#667273 — Re: Even Prolog now depends on China (Was: Meta is Dust: Yann LeCun crushed by Behemoth China)

On 11/13/2025 10:13 AM, Mild Shock wrote:
> Hi,
>
> Because the Prolog community has dummbed itself
> down over the last years. You don't find something
> mildly interesting published by Prologers.
>
> On the other hand Behemoth China has easy game:
>
> 8x Authors China:
>
> Abductive Logical Rule Induction by Bridging Inductive
> Logic Programming and Multimodal Large Language Models
> https://arxiv.org/pdf/2509.21874
>
> 2x Authors China:
>
> Domain-Contextualized Concept Graphs:
> A Computable Framework for Knowledge Representation
> https://arxiv.org/abs/2510.16802
>
> Have Fun!
>
> Bye
>
> Mild Shock schrieb:
>> Hi,
>>
>> How it started:
>>
>> RIP Deepseek. We have a new #1 open-source AI model
>> https://www.youtube.com/watch?v=xt6_zIKeX6A
>>
>> How its going:
>>
>> Meta’s AI Genius Just Quit — Even Zuckerberg Seems Surprised.
>> https://www.youtube.com/watch?v=W2tr1Q3D1ZI
>>
>> I guess Yann LeCun was not paying attention
>> to the transition of LLM (Large Language Models)
>> to LRM (Large Reasoning Models).
>>
>> Bye
>
>

Oh, what's in it for you? Is that going to
assist your crypto-ponzi schemes, miRNA-pushing,
and now deepfake services?

GPUs/FPUs are an interesting market niche,
they can be made of very cheap silicon,
and with many defects, so that their large
die areas which is cheap silicon provide
floating-point units for neural-net implementations,
or otherwise the usual sorts of approximations,
while that each one is different,
a unique sort of snowflake.

It's funny the other day it was discovered
that networking interface multi-homing and
cache-hiding was sort of trivially exploitable,
that being old news, that also usual sorts of
implementations also poison it the other way,
and now lots of false leads off of multihoming
have new leads.

Yeah, it's so that that Primary R&D is the
most predictive driver of GDP, then though
about the people, who generally resist
expropriation, of what they've built.


Is this relevant to thea-theory about
the mathematics of continuity and infinity,
and "the logic", and about the field of
science known as relativity theory?

https://aclanthology.org

"Behemoth" or "Leviathan"?
There goes Hobbes again, ....

[toc] | [prev] | [standalone]

Back to top | Article view | sci.physics.relativity

csiph-web