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

Groups > sci.math > #640729

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

Cross-posted to 3 groups.

Show all headers | View raw

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
>>>
>>
> 

Back to sci.math | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Vanishing Point . [Le Dot] Mild Shock <janburse@fastmail.fm> - 2025-10-05 00:52 +0200
  Lets compare AI data centers (Re: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-10-05 01:05 +0200
    USA domestic chips for the never ending crunch (Re: Lets compare AI data centers) Mild Shock <janburse@fastmail.fm> - 2025-10-05 01:19 +0200
      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
  Re: Vanishing Point . [Le Dot] Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-04 18:38 -0700
    Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). (Was: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-10-05 10:09 +0200
      Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) Mild Shock <janburse@fastmail.fm> - 2025-10-05 10:29 +0200
        Re: Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-05 10:29 -0700
        Re: Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) kinak <kin@mob.net.inv> - 2025-10-05 18:57 +0100
          Re: Holy Schrimp Jesus: The Internet is Dead [Rossy Boy dethroned?] (Was: Creative Commons Attribution-ShareAlike 4.0 International License) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-05 11:06 -0700
    British writer Arthur C. Clarke (Re: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-10-05 19:33 +0200
      Aryabhatta of Bihar [Indian Mathematician-Astronomer] (Re: British writer Arthur C. Clarke) Mild Shock <janburse@fastmail.fm> - 2025-10-05 19:34 +0200
      Re: British writer Arthur C. Clarke (Re: Vanishing Point . [Le Dot]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2025-10-05 11:06 -0700
  Knight Rider (2025/2026) will kill us all (Was: Vanishing Point . [Le Dot]) Mild Shock <janburse@fastmail.fm> - 2025-11-13 21:52 +0100
    The AGI Gambit: Hype vs. Reality (Re: Knight Rider (2025/2026) will kill us all) Mild Shock <janburse@fastmail.fm> - 2025-11-13 21:59 +0100
      Stable Diffusion with Control Net (Re: The AGI Gambit: Hype vs. Reality) Mild Shock <janburse@fastmail.fm> - 2025-11-13 23:04 +0100

csiph-web