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

Groups > sci.math > #628865 > unrolled thread

Minimal Logics in the 2020's: A Meteoric Rise

Back to article view | Back to sci.math

Contents

  Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-05 00:05 +0200
    Re: Minimal Logics in the 2020's: A Meteoric Rise sobriquet <dohduhdah@yahoo.com> - 2024-07-05 03:50 +0200
      Re: Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-05 04:06 +0200
        Re: Minimal Logics in the 2020's: A Meteoric Rise sobriquet <dohduhdah@yahoo.com> - 2024-07-05 05:24 +0200
          Re: Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-05 06:47 +0200
            Re: Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-05 06:48 +0200
    The curse of Negri & Plato (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-05 04:07 +0200
      Re: The curse of Negri & Plato (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-05 04:08 +0200
        Euklid: Am I a joke to you? (Re: The curse of Negri & Plato) Mild Shock <janburse@fastmail.fm> - 2024-07-13 08:18 +0200
    Re: Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-05 06:49 +0200
      Re: Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-07 23:10 +0200
        Re: Minimal Logics in the 2020's: A Meteoric Rise Mild Shock <janburse@fastmail.fm> - 2024-07-07 23:18 +0200
    French Philosophy in 2024 (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-12 11:30 +0200
      Re: French Philosophy in 2024 (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-12 11:38 +0200
        Corona isn't over 2024 (Was: French Philosophy in 2024) Mild Shock <janburse@fastmail.fm> - 2024-07-12 12:23 +0200
        Re: Corona isn't over 2024 (Was: French Philosophy in 2024) Mild Shock <janburse@fastmail.fm> - 2024-07-12 12:36 +0200
    The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-13 10:33 +0200
    Re: The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-13 10:56 +0200
      Re: The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-14 00:04 +0200
        Re: The error in Jan von Platos presentation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-14 00:14 +0200
    Distinction between Computation & Derivation (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-22 12:58 +0200
    Prolegomena by Rappaport (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-07-31 22:16 +0200
      2nd Cognitive Turn ~~> no Bayesian Brain (Re: Prolegomena by Rappaport) Mild Shock <janburse@fastmail.fm> - 2024-08-03 22:51 +0200
        Ok I made a joke, sorry (Re: 2nd Cognitive Turn ~~> no Bayesian Brain) Mild Shock <janburse@fastmail.fm> - 2024-08-03 23:48 +0200
          Re: Ok I made a joke, sorry (Re: 2nd Cognitive Turn ~~> no Bayesian Brain) Mild Shock <janburse@fastmail.fm> - 2024-08-04 00:00 +0200
          bullshit bullshit bullshit (Was: Ok I made a joke, sorry) Mild Shock <janburse@fastmail.fm> - 2024-08-04 00:13 +0200
    The two rules (Was: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-08-04 00:58 +0200
      Re: The two rules (Was: Minimal Logics in the 2020's: A Meteoric Rise) Moebius <invalid@example.invalid> - 2024-08-04 01:45 +0200
    The anchoring problem in a real world philosopher (Re: LLM and Prolog, a Marriage in Heaven?) Mild Shock <janburse@fastmail.fm> - 2024-08-08 17:11 +0200
      Long life learning also for real world philosophers? (Re: The anchoring problem in a real world philosopher) Mild Shock <janburse@fastmail.fm> - 2024-08-08 17:19 +0200
    Prolog for the pre frontal cortex (PFC) (Was: LLM and Prolog, a Marriage in Heaven?) Mild Shock <janburse@fastmail.fm> - 2024-08-28 20:46 +0200
    Holy Shit: AI is cheaper than Humans (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-09-01 22:38 +0200
      AI robots from Disney (Re: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-01 23:20 +0200
      Re: Holy Shit: AI is cheaper than Humans (Re: Minimal Logics in the 2020's: A Meteoric Rise) Jim Burns <james.g.burns@att.net> - 2024-09-02 09:32 -0400
        Re: Holy Shit: AI is cheaper than Humans (Re: Minimal Logics in the 2020's: A Meteoric Rise) Ross Finlayson <ross.a.finlayson@gmail.com> - 2024-09-02 09:30 -0700
          There is only a nature article about "low carbon emission" (Was: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-02 19:02 +0200
      I can't stand Mira Murati's Eyewash (Re: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-03 12:03 +0200
        After blue, green why not start yellow (Re: I can't stand Mira Murati's Eyewash) Mild Shock <janburse@fastmail.fm> - 2024-09-03 17:58 +0200
          miramurati bye bye (Re: After blue, green why not start yellow) Mild Shock <janburse@fastmail.fm> - 2024-09-25 22:10 +0200
      Safe Superintelligence (SSI): Now they are dancing Mild Shock <janburse@fastmail.fm> - 2024-09-05 19:52 +0200
        Re: Safe Superintelligence (SSI): Now they are dancing Mild Shock <janburse@fastmail.fm> - 2024-09-05 23:52 +0200
          Salem Aleikum: Maxwella's Equations (Re: Safe Superintelligence (SSI): Now they are dancing) Mild Shock <janburse@fastmail.fm> - 2024-09-09 13:20 +0200
            non judicium, sed latrocinium (Re: Salem Aleikum: Maxwella's Equations) Mild Shock <janburse@fastmail.fm> - 2024-09-10 08:57 +0200
        Internet was made for cats (Was: Safe Superintelligence (SSI): Now they are dancing) Mild Shock <janburse@fastmail.fm> - 2024-09-11 20:11 +0200
          I was there, 3000 years ago (Re: Internet was made for cats) Mild Shock <janburse@fastmail.fm> - 2024-09-13 13:00 +0200
            Even Haitians are now voting for Trump (Re: I was there, 3000 years ago (Re: Internet was made for cats)) Mild Shock <janburse@fastmail.fm> - 2024-09-13 13:03 +0200
          supply chain attack (Re: Internet was made for cats) Mild Shock <janburse@fastmail.fm> - 2024-09-17 22:19 +0200
            Polyfill Supply Chain Attack (Re: supply chain attack) Mild Shock <janburse@fastmail.fm> - 2024-10-11 09:13 +0200
      USA is shitting its pants (Re: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-16 00:23 +0200
        scryer prolog is dead, BILAI instead? Re: USA is shitting its pants (Re: Holy Shit: AI is cheaper than Humans) Mild Shock <janburse@fastmail.fm> - 2024-09-18 15:44 +0200
          Microsoft is plagiarizing my Invention [LLMs under the hood] Mild Shock <janburse@fastmail.fm> - 2024-10-08 16:06 +0200
            Geoffrey Hinton / Nobelpreis für Physik [Re: Microsoft is plagiarizing my Invention [LLMs under the hood]] Mild Shock <janburse@fastmail.fm> - 2024-10-08 16:06 +0200
    "Emotional AI" and "Spiritual AI" (Re: Minimal Logics in the 2020's: A Meteoric Rise) Mild Shock <janburse@fastmail.fm> - 2024-10-03 12:29 +0200
      Oh shit, too late! (Re: "Emotional AI" and "Spiritual AI" (Re: Minimal Logics in the 2020's: A Meteoric Rise)) Mild Shock <janburse@fastmail.fm> - 2024-10-03 12:41 +0200

Page 3 of 3 — ← Prev page 1 2 [3]

#631044 — Re: Safe Superintelligence (SSI): Now they are dancing

Its amazing how we are in the mists of new buzzwords
such as superintelligence, superhuman, etc… I used
the term “long inferencing” in one post somewhere

for a combination of LLM with a more capable inferencing,
compared to current LLMs that rather show “short inferencing”.
Then just yesterday its was Strawberry and Orion, as the

next leap by OpenAI. Is the leap getting out of control?
OpenAI wanted to do “Superalignment” but lost a figure head.
Now there is new company which wants to do safety-focused

non-narrow AI. But they chose another name. If I translate
superhuman to German I might end with “Übermensch”,
first used by Nietzsche and later by Hitler and the

Nazi regime. How ironic!

Nick Bostrom - Superintelligence
https://www.orellfuessli.ch/shop/home/artikeldetails/A1037878459

Mild Shock schrieb:
> Hi,
> 
> SAN FRANCISCO/NEW YORK, Sept 4 - Safe
> Superintelligence (SSI), newly co-founded by OpenAI's
> former chief scientist Ilya Sutskever, has raised $1
> billion in cash to help develop safe artificial
> intelligence systems that far surpass human
> capabilities, company executives told Reuters.
> https://www.reuters.com/technology/artificial-intelligence/openai-co-founder-sutskevers-new-safety-focused-ai-startup-ssi-raises-1-billion-2024-09-04/ 
> 
> 
> Now they are dancing
> https://twitter.com/AIForHumansShow/status/1831465601782706352
> 
> Bye

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

#631173 — Salem Aleikum: Maxwella's Equations (Re: Safe Superintelligence (SSI): Now they are dancing)

Hi,

Not sure whether this cinematic master piece
contains a rendition when I was hunted recently
by a virus and had some hypomanic episodes.

But the chapter "Electromagnetic Waves" is fun:

Three Thousand Years of Longing
https://youtu.be/id8-z5vANvc?t=3881

Bye

Mild Shock schrieb:
> Its amazing how we are in the mists of new buzzwords
> such as superintelligence, superhuman, etc… I used
> the term “long inferencing” in one post somewhere
> 
> for a combination of LLM with a more capable inferencing,
> compared to current LLMs that rather show “short inferencing”.
> Then just yesterday its was Strawberry and Orion, as the
> 
> next leap by OpenAI. Is the leap getting out of control?
> OpenAI wanted to do “Superalignment” but lost a figure head.
> Now there is new company which wants to do safety-focused
> 
> non-narrow AI. But they chose another name. If I translate
> superhuman to German I might end with “Übermensch”,
> first used by Nietzsche and later by Hitler and the
> 
> Nazi regime. How ironic!
> 
> Nick Bostrom - Superintelligence
> https://www.orellfuessli.ch/shop/home/artikeldetails/A1037878459
> 
> Mild Shock schrieb:
>> Hi,
>>
>> SAN FRANCISCO/NEW YORK, Sept 4 - Safe
>> Superintelligence (SSI), newly co-founded by OpenAI's
>> former chief scientist Ilya Sutskever, has raised $1
>> billion in cash to help develop safe artificial
>> intelligence systems that far surpass human
>> capabilities, company executives told Reuters.
>> https://www.reuters.com/technology/artificial-intelligence/openai-co-founder-sutskevers-new-safety-focused-ai-startup-ssi-raises-1-billion-2024-09-04/ 
>>
>>
>> Now they are dancing
>> https://twitter.com/AIForHumansShow/status/1831465601782706352
>>
>> Bye

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

#631232 — non judicium, sed latrocinium (Re: Salem Aleikum: Maxwella's Equations)

Hi,

That a Djin can procreate with a Human,
looks like variation of this theme:

Die „Räubersynode" von Ephesos
https://www.youtube.com/watch?v=giIGyg07UO0

But how is Artificial Intelligence born?

Bye

Mild Shock schrieb:
> Hi,
> 
> Not sure whether this cinematic master piece
> contains a rendition when I was hunted recently
> by a virus and had some hypomanic episodes.
> 
> But the chapter "Electromagnetic Waves" is fun:
> 
> Three Thousand Years of Longing
> https://youtu.be/id8-z5vANvc?t=3881
> 
> Bye
> 
> Mild Shock schrieb:
>> Its amazing how we are in the mists of new buzzwords
>> such as superintelligence, superhuman, etc… I used
>> the term “long inferencing” in one post somewhere
>>
>> for a combination of LLM with a more capable inferencing,
>> compared to current LLMs that rather show “short inferencing”.
>> Then just yesterday its was Strawberry and Orion, as the
>>
>> next leap by OpenAI. Is the leap getting out of control?
>> OpenAI wanted to do “Superalignment” but lost a figure head.
>> Now there is new company which wants to do safety-focused
>>
>> non-narrow AI. But they chose another name. If I translate
>> superhuman to German I might end with “Übermensch”,
>> first used by Nietzsche and later by Hitler and the
>>
>> Nazi regime. How ironic!
>>
>> Nick Bostrom - Superintelligence
>> https://www.orellfuessli.ch/shop/home/artikeldetails/A1037878459
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> SAN FRANCISCO/NEW YORK, Sept 4 - Safe
>>> Superintelligence (SSI), newly co-founded by OpenAI's
>>> former chief scientist Ilya Sutskever, has raised $1
>>> billion in cash to help develop safe artificial
>>> intelligence systems that far surpass human
>>> capabilities, company executives told Reuters.
>>> https://www.reuters.com/technology/artificial-intelligence/openai-co-founder-sutskevers-new-safety-focused-ai-startup-ssi-raises-1-billion-2024-09-04/ 
>>>
>>>
>>> Now they are dancing
>>> https://twitter.com/AIForHumansShow/status/1831465601782706352
>>>
>>> Bye
> 

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

#631306 — Internet was made for cats (Was: Safe Superintelligence (SSI): Now they are dancing)

Trump: They're eating the dogs, the cats
https://www.youtube.com/watch?v=5llMaZ80ErY

https://twitter.com/search?q=trump+cat

Mild Shock schrieb:
> Hi,
> 
> SAN FRANCISCO/NEW YORK, Sept 4 - Safe
> Superintelligence (SSI), newly co-founded by OpenAI's
> former chief scientist Ilya Sutskever, has raised $1
> billion in cash to help develop safe artificial
> intelligence systems that far surpass human
> capabilities, company executives told Reuters.
> https://www.reuters.com/technology/artificial-intelligence/openai-co-founder-sutskevers-new-safety-focused-ai-startup-ssi-raises-1-billion-2024-09-04/ 
> 
> 
> Now they are dancing
> https://twitter.com/AIForHumansShow/status/1831465601782706352
> 
> Bye
> 
> Mild Shock schrieb:
>>
>> The carbon emissions of writing and illustrating
>> are lower for AI than for humans
>> https://www.nature.com/articles/s41598-024-54271-x
>>
>> Perplexity CEO Aravind Srinivas says that the cost per
>> query in AI models has decreased by 100x in the past
>> 2 years and quality will improve as hallucinations
>> decrease 10x per year
>> https://twitter.com/tsarnick/status/1830045611036721254
>>
>> Disclaimer: Can't verify the later claim... need to find a paper.
>>
>> Mild Shock schrieb:
>>> Could be a wake-up call this many participants
>>> already in the commitee, that the whole logic
>>> world was asleep for many years:
>>>
>>> Non-Classical Logics. Theory and Applications XI,
>>> 5-8 September 2024, Lodz (Poland)
>>> https://easychair.org/cfp/NCL24
>>>
>>> Why is Minimal Logic at the core of many things?
>>> Because it is the logic of Curry-Howard isomorphism
>>> for simple types:
>>>
>>> ----------------
>>> Γ ∪ { A } ⊢ A
>>>
>>> Γ ∪ { A } ⊢ B
>>> ----------------
>>> Γ ⊢ A → B
>>>
>>> Γ ⊢ A → B           Δ ⊢ A
>>> ----------------------------
>>> Γ ∪ Δ ⊢ B
>>>
>>> And funny things can happen, especially when people
>>> hallucinate duality or think symmetry is given, for
>>> example in newer inventions such as λμ-calculus,
>>>
>>> but then omg ~~p => p is nevertheless not provable,
>>> because they forgot an inference rule. LoL
>>>
>>> Recommended reading so far:
>>>
>>> Propositional Logics Related to Heyting’s and Johansson’s
>>> February 2008 - Krister Segerberg
>>> https://www.researchgate.net/publication/228036664
>>>
>>> The Logic of Church and Curry
>>> Jonathan P. Seldin - 2009
>>> https://www.sciencedirect.com/handbook/handbook-of-the-history-of-logic/vol/5/suppl/C 
>>>
>>>
>>> Meanwhile I am going back to my tinkering with my
>>> Prolog system, which even provides a more primitive
>>> logic than minimal logic, pure Prolog is minimal
>>>
>>> logic without embedded implication.
>>
> 

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

#631354 — I was there, 3000 years ago (Re: Internet was made for cats)

Hi,

MIS is acronym for management information systems.
In the past, people from MIS, offered consulting by means
balanced scorecard, which could be benefitial for companies:

Balanced Scorecard
https://en.wikipedia.org/wiki/Balanced_scorecard

Now after big data, artificial intelligence, etc.. we can
do text scraping and venture into Luhmanns Autopoiesis,
d.h. Selbsterhaltung durch Nabelschau:

Are we on the right track? an update to Lyytinen
et al.’s commentary on why the old world cannot publish
https://www.tandfonline.com/doi/pdf/10.1080/0960085X.2021.1940324

LoL

Gruss, Jan

P.S.: Autopoiesis
Autopoietische Systeme erzeugen und ermöglichen sich
selbst. "Als autopoietisch wollen wir Systeme bezeichnen, die
die Elemente, aus denen sie bestehen, durch die Elementen,
aus denen sie bestehen, selbst produzieren und reproduzieren. (...)
Ein autopoietisches System ist ein selbstreferenziell-zirkulär
geschlossener Zusammenhang von Operationen."
https://luhmann.fandom.com/de/wiki/Autopoiesis

Mild Shock schrieb:
> 
> Trump: They're eating the dogs, the cats
> https://www.youtube.com/watch?v=5llMaZ80ErY
> 
> https://twitter.com/search?q=trump+cat

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

#631355 — Even Haitians are now voting for Trump (Re: I was there, 3000 years ago (Re: Internet was made for cats))

Hi,

Given this theory from cognitive science, Trump
did a "home run" during his encounter with Kamala.
The internet was made for cats:

"The anchoring effect is a psychological phenomenon in
which an individual's judgments or decisions are influenced
by a reference point or "anchor" which can be completely irrelevant."
https://en.wikipedia.org/wiki/Anchoring_effect

But not only Trump wants to get a foothold in my
brain. Apple is spamming me with Artificial Intelligence
everywhere suggestions:

"Den nächsten Schritt in deiner schulischen Laufbahn
zu absolvieren, ist aufregend und herausfordernd zugleich.
KI-gestützte Tools haben das Potenzial, dir die meisten deiner
Studien zu erleichtern und eine steile Lernkurve zu ermöglichen."
https://apps.apple.com/ch/story/id1749178332

Suggesting its the new normal to use AI in schools and
university. Not stigmatized, rather a unique selling proposition.

Bye

Mild Shock schrieb:
> Hi,
> 
> MIS is acronym for management information systems.
> In the past, people from MIS, offered consulting by means
> balanced scorecard, which could be benefitial for companies:
> 
> Balanced Scorecard
> https://en.wikipedia.org/wiki/Balanced_scorecard
> 
> Now after big data, artificial intelligence, etc.. we can
> do text scraping and venture into Luhmanns Autopoiesis,
> d.h. Selbsterhaltung durch Nabelschau:
> 
> Are we on the right track? an update to Lyytinen
> et al.’s commentary on why the old world cannot publish
> https://www.tandfonline.com/doi/pdf/10.1080/0960085X.2021.1940324
> 
> LoL
> 
> Gruss, Jan
> 
> P.S.: Autopoiesis
> Autopoietische Systeme erzeugen und ermöglichen sich
> selbst. "Als autopoietisch wollen wir Systeme bezeichnen, die
> die Elemente, aus denen sie bestehen, durch die Elementen,
> aus denen sie bestehen, selbst produzieren und reproduzieren. (...)
> Ein autopoietisches System ist ein selbstreferenziell-zirkulär
> geschlossener Zusammenhang von Operationen."
> https://luhmann.fandom.com/de/wiki/Autopoiesis
> 
> Mild Shock schrieb:
>>
>> Trump: They're eating the dogs, the cats
>> https://www.youtube.com/watch?v=5llMaZ80ErY
>>
>> https://twitter.com/search?q=trump+cat
> 
> 

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

#631470 — supply chain attack (Re: Internet was made for cats)

How it started:

How Hezbollah used pagers and couriers to counter
July 9, 2024
https://www.reuters.com/world/middle-east/pagers-drones-how-hezbollah-aims-counter-israels-high-tech-surveillance-2024-07-09/

How its going:

What we know about the Hezbollah pager explosions
Sept 17, 2024
https://www.bbc.com/news/articles/cz04m913m49o

Mild Shock schrieb:
> 
> Trump: They're eating the dogs, the cats
> https://www.youtube.com/watch?v=5llMaZ80ErY
> 
> https://twitter.com/search?q=trump+cat

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

#632304 — Polyfill Supply Chain Attack (Re: supply chain attack)

Shitty JavaScript "Ecosystem":

The Internet Archive Has Been Hacked - October 10, 2024
https://hackaday.com/2024/10/10/the-internet-archive-has-been-hacked/

Polyfill Supply Chain Attack: Details and Fixes - July 9, 2024
https://fossa.com/blog/polyfill-supply-chain-attack-details-fixes/

Mild Shock schrieb:
> 
> How it started:
> 
> How Hezbollah used pagers and couriers to counter
> July 9, 2024
> https://www.reuters.com/world/middle-east/pagers-drones-how-hezbollah-aims-counter-israels-high-tech-surveillance-2024-07-09/ 
> 
> 
> How its going:
> 
> What we know about the Hezbollah pager explosions
> Sept 17, 2024
> https://www.bbc.com/news/articles/cz04m913m49o
> 
> Mild Shock schrieb:
>>
>> Trump: They're eating the dogs, the cats
>> https://www.youtube.com/watch?v=5llMaZ80ErY
>>
>> https://twitter.com/search?q=trump+cat

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

#631440 — USA is shitting its pants (Re: Holy Shit: AI is cheaper than Humans)

You know USA has a problem,
when Oracle enters the race:

To source the 131,072 GPU Al "supercluster,"
Larry Ellison, appealed directly to Jensen Huang,
during a dinner joined by Elon Musk at Nobu.
"I would describe the dinner as me and Elon
begging Jensen for GPUs. Please take our money.
We need you to take more of our money. Please!”
https://twitter.com/benitoz/status/1834741314740756621

Meanwhile a contender in Video GenAI
FLUX.1 from Germany, Hurray! With Open Source:

OK. Now I'm Scared... AI Better Than Reality
https://www.youtube.com/watch?v=cvMAVWDD-DU

Mild Shock schrieb:
> 
> The carbon emissions of writing and illustrating
> are lower for AI than for humans
> https://www.nature.com/articles/s41598-024-54271-x
> 
> Perplexity CEO Aravind Srinivas says that the cost per
> query in AI models has decreased by 100x in the past
> 2 years and quality will improve as hallucinations
> decrease 10x per year
> https://twitter.com/tsarnick/status/1830045611036721254
> 
> Disclaimer: Can't verify the later claim... need to find a paper.
> 
> Mild Shock schrieb:
>> Could be a wake-up call this many participants
>> already in the commitee, that the whole logic
>> world was asleep for many years:
>>
>> Non-Classical Logics. Theory and Applications XI,
>> 5-8 September 2024, Lodz (Poland)
>> https://easychair.org/cfp/NCL24
>>
>> Why is Minimal Logic at the core of many things?
>> Because it is the logic of Curry-Howard isomorphism
>> for simple types:
>>
>> ----------------
>> Γ ∪ { A } ⊢ A
>>
>> Γ ∪ { A } ⊢ B
>> ----------------
>> Γ ⊢ A → B
>>
>> Γ ⊢ A → B           Δ ⊢ A
>> ----------------------------
>> Γ ∪ Δ ⊢ B
>>
>> And funny things can happen, especially when people
>> hallucinate duality or think symmetry is given, for
>> example in newer inventions such as λμ-calculus,
>>
>> but then omg ~~p => p is nevertheless not provable,
>> because they forgot an inference rule. LoL
>>
>> Recommended reading so far:
>>
>> Propositional Logics Related to Heyting’s and Johansson’s
>> February 2008 - Krister Segerberg
>> https://www.researchgate.net/publication/228036664
>>
>> The Logic of Church and Curry
>> Jonathan P. Seldin - 2009
>> https://www.sciencedirect.com/handbook/handbook-of-the-history-of-logic/vol/5/suppl/C 
>>
>>
>> Meanwhile I am going back to my tinkering with my
>> Prolog system, which even provides a more primitive
>> logic than minimal logic, pure Prolog is minimal
>>
>> logic without embedded implication.
> 

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

#631478 — scryer prolog is dead, BILAI instead? Re: USA is shitting its pants (Re: Holy Shit: AI is cheaper than Humans)

The biggest flop in logic programming
history, scryer prolog is dead. The poor
thing is a prolog system without garbage

collection, not very useful. So how will
Austria get out of all this?
With 50 PhDs and 10 Postdocs?

"To develop its foundations, BILAI employs a
Bilateral AI approach, effectively combining
sub-symbolic AI (neural networks and machine learning)
with symbolic AI (logic, knowledge representation,
and reasoning) in various ways."

https://www.bilateral-ai.net/jobs/.

LoL

Mild Shock schrieb:
> 
> You know USA has a problem,
> when Oracle enters the race:
> 
> To source the 131,072 GPU Al "supercluster,"
> Larry Ellison, appealed directly to Jensen Huang,
> during a dinner joined by Elon Musk at Nobu.
> "I would describe the dinner as me and Elon
> begging Jensen for GPUs. Please take our money.
> We need you to take more of our money. Please!”
> https://twitter.com/benitoz/status/1834741314740756621
> 
> Meanwhile a contender in Video GenAI
> FLUX.1 from Germany, Hurray! With Open Source:
> 
> OK. Now I'm Scared... AI Better Than Reality
> https://www.youtube.com/watch?v=cvMAVWDD-DU
> 
> Mild Shock schrieb:
>>
>> The carbon emissions of writing and illustrating
>> are lower for AI than for humans
>> https://www.nature.com/articles/s41598-024-54271-x
>>
>> Perplexity CEO Aravind Srinivas says that the cost per
>> query in AI models has decreased by 100x in the past
>> 2 years and quality will improve as hallucinations
>> decrease 10x per year
>> https://twitter.com/tsarnick/status/1830045611036721254
>>
>> Disclaimer: Can't verify the later claim... need to find a paper.
>>
>> Mild Shock schrieb:
>>> Could be a wake-up call this many participants
>>> already in the commitee, that the whole logic
>>> world was asleep for many years:
>>>
>>> Non-Classical Logics. Theory and Applications XI,
>>> 5-8 September 2024, Lodz (Poland)
>>> https://easychair.org/cfp/NCL24
>>>
>>> Why is Minimal Logic at the core of many things?
>>> Because it is the logic of Curry-Howard isomorphism
>>> for simple types:
>>>
>>> ----------------
>>> Γ ∪ { A } ⊢ A
>>>
>>> Γ ∪ { A } ⊢ B
>>> ----------------
>>> Γ ⊢ A → B
>>>
>>> Γ ⊢ A → B           Δ ⊢ A
>>> ----------------------------
>>> Γ ∪ Δ ⊢ B
>>>
>>> And funny things can happen, especially when people
>>> hallucinate duality or think symmetry is given, for
>>> example in newer inventions such as λμ-calculus,
>>>
>>> but then omg ~~p => p is nevertheless not provable,
>>> because they forgot an inference rule. LoL
>>>
>>> Recommended reading so far:
>>>
>>> Propositional Logics Related to Heyting’s and Johansson’s
>>> February 2008 - Krister Segerberg
>>> https://www.researchgate.net/publication/228036664
>>>
>>> The Logic of Church and Curry
>>> Jonathan P. Seldin - 2009
>>> https://www.sciencedirect.com/handbook/handbook-of-the-history-of-logic/vol/5/suppl/C 
>>>
>>>
>>> Meanwhile I am going back to my tinkering with my
>>> Prolog system, which even provides a more primitive
>>> logic than minimal logic, pure Prolog is minimal
>>>
>>> logic without embedded implication.
>>
> 

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

#632145 — Microsoft is plagiarizing my Invention [LLMs under the hood]

will probably never get a Turing Award or something
for what I did 23 years ago. Why is its reading
count on research gate suddently going up?

Knowledge, Planning and Language,
November 2001

I guess because of this, the same topic takled by
Microsofts recent model GRIN. Shit. I really should
find some investor and pump up a start up!

"Mixture-of-Experts (MoE) models scale more
effectively than dense models due to sparse
computation through expert routing, selectively
activating only a small subset of expert modules."
https://arxiv.org/pdf/2409.12136

But somehow I am happy with my dolce vita as
it is now... Or maybe I am decepting myself?

P.S.: From the GRIN paper, here you see how
expert domains modules relate with each other:

Figure 6 (b): MoE Routing distribution similarity
across MMLU 57 tasks for the control recipe.

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

#632146 — Geoffrey Hinton / Nobelpreis für Physik [Re: Microsoft is plagiarizing my Invention [LLMs under the hood]]

Maybe these guys were earlier:

Jacobs, R. A., Jordan, M. I., Nowlan, S. J., and Hinton,
G. E. Adaptive mixtures of local experts.
Neural Computation, 1991.

And more connectionist than my symbolic approach.

Disclaimer: Never read the paper yet.

Mild Shock schrieb:
> will probably never get a Turing Award or something
> for what I did 23 years ago. Why is its reading
> count on research gate suddently going up?
> 
> Knowledge, Planning and Language,
> November 2001
> 
> I guess because of this, the same topic takled by
> Microsofts recent model GRIN. Shit. I really should
> find some investor and pump up a start up!
> 
> "Mixture-of-Experts (MoE) models scale more
> effectively than dense models due to sparse
> computation through expert routing, selectively
> activating only a small subset of expert modules."
> https://arxiv.org/pdf/2409.12136
> 
> But somehow I am happy with my dolce vita as
> it is now... Or maybe I am decepting myself?
> 
> P.S.: From the GRIN paper, here you see how
> expert domains modules relate with each other:
> 
> Figure 6 (b): MoE Routing distribution similarity
> across MMLU 57 tasks for the control recipe.

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

#631834 — "Emotional AI" and "Spiritual AI" (Re: Minimal Logics in the 2020's: A Meteoric Rise)

Hi,

ChatGPT is rather dry, giving me always some
choice lists displaying his knowledge. The
interaction is not very "involving".

Could this be improved. There are possibly two
traits missing:

Feelings:
- Emotional states
- Temporariness
- Reaction to external circumstances
- Changeability
- Subjective sensations

Soul:
- Spirituality
- Immortality
- Innermost being
- Essence of an individual
- Deep, enduring aspects of human existence

Mostlikely we will see both traits added to AI.
"Emotional AI" has been more discussed already,
"Spiritual AI" seems to be rather new.

In a "Spiritual AI" Faith would probably be important,
which is probably at the upper end of credulous
reasoning. This means that such a ChatGPT could

also babble that in a Prisoner Dilemma Game,
cooperation is always the better alternative,
e.g. promoting "altruistic" motives, etc.

I also suspect that “Spiritual AI” and “Emotional
AI” could coexist.  Many religions give Cosmopolitan
magazin style life advice, and not just theological

dogmas. There will probably soon be an “Inner Engineering”
app from Sadhguru that works with AI. Sadhguru is
also sometimes satirically referred to as Chadguru:

Sat Guru Parody | Carryminati
https://www.youtube.com/watch?v=PlZqxP5MXFs

Mild Shock schrieb:
> Could be a wake-up call this many participants
> already in the commitee, that the whole logic
> world was asleep for many years:
> 
> Non-Classical Logics. Theory and Applications XI,
> 5-8 September 2024, Lodz (Poland)
> https://easychair.org/cfp/NCL24
> 
> Why is Minimal Logic at the core of many things?
> Because it is the logic of Curry-Howard isomorphism
> for simple types:
> 
> ----------------
> Γ ∪ { A } ⊢ A
> 
> Γ ∪ { A } ⊢ B
> ----------------
> Γ ⊢ A → B
> 
> Γ ⊢ A → B           Δ ⊢ A
> ----------------------------
> Γ ∪ Δ ⊢ B
> 
> And funny things can happen, especially when people
> hallucinate duality or think symmetry is given, for
> example in newer inventions such as λμ-calculus,
> 
> but then omg ~~p => p is nevertheless not provable,
> because they forgot an inference rule. LoL
> 
> Recommended reading so far:
> 
> Propositional Logics Related to Heyting’s and Johansson’s
> February 2008 - Krister Segerberg
> https://www.researchgate.net/publication/228036664
> 
> The Logic of Church and Curry
> Jonathan P. Seldin - 2009
> https://www.sciencedirect.com/handbook/handbook-of-the-history-of-logic/vol/5/suppl/C 
> 
> 
> Meanwhile I am going back to my tinkering with my
> Prolog system, which even provides a more primitive
> logic than minimal logic, pure Prolog is minimal
> 
> logic without embedded implication.

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

#631835 — Oh shit, too late! (Re: "Emotional AI" and "Spiritual AI" (Re: Minimal Logics in the 2020's: A Meteoric Rise))

Hi,

ChatGPT is currently showing new tricks to me
and would like to adapt its dialogue style:

"Got it! Emotionally connected communication can
indeed be concise and efficient, without losing depth.
I can focus more on direct responses that still acknowledge
emotional nuances, while avoiding unnecessary elaboration.

Would you like me to adapt this style right away?"

After I switched back to "elaboration", the thing gives
me information about "Spiritual AI":

"- Mindfulness and Meditation Apps: Apps like
Headspace and Calm use AI to guide meditation
and promote mindfulness, which are often
associated with spiritual growth.

- AI-driven Chatbots for Spiritual Guidance: For
example, in 2017, a chatbot named Jwitness was
designed to answer questions based on Jehovah's
Witness teachings.

- AI Prayer Companions: Some faith communities
are experimenting with AI that assists in
prayer or reflection

- Platforms that promote deeper philosophical
discussions, like Replika, which is designed to
engage in thoughtful and sometimes
existential conversations

- For instance, Woebot or Wysa help users navigate
emotions but also touch on existential themes
like purpose and fulfillment."

Bye

Mild Shock schrieb:
> Hi,
> 
> ChatGPT is rather dry, giving me always some
> choice lists displaying his knowledge. The
> interaction is not very "involving".
> 
> Could this be improved. There are possibly two
> traits missing:
> 
> Feelings:
> - Emotional states
> - Temporariness
> - Reaction to external circumstances
> - Changeability
> - Subjective sensations
> 
> Soul:
> - Spirituality
> - Immortality
> - Innermost being
> - Essence of an individual
> - Deep, enduring aspects of human existence
> 
> Mostlikely we will see both traits added to AI.
> "Emotional AI" has been more discussed already,
> "Spiritual AI" seems to be rather new.
> 
> In a "Spiritual AI" Faith would probably be important,
> which is probably at the upper end of credulous
> reasoning. This means that such a ChatGPT could
> 
> also babble that in a Prisoner Dilemma Game,
> cooperation is always the better alternative,
> e.g. promoting "altruistic" motives, etc.
> 
> I also suspect that “Spiritual AI” and “Emotional
> AI” could coexist.  Many religions give Cosmopolitan
> magazin style life advice, and not just theological
> 
> dogmas. There will probably soon be an “Inner Engineering”
> app from Sadhguru that works with AI. Sadhguru is
> also sometimes satirically referred to as Chadguru:
> 
> Sat Guru Parody | Carryminati
> https://www.youtube.com/watch?v=PlZqxP5MXFs
> 
> Mild Shock schrieb:
>> Could be a wake-up call this many participants
>> already in the commitee, that the whole logic
>> world was asleep for many years:
>>
>> Non-Classical Logics. Theory and Applications XI,
>> 5-8 September 2024, Lodz (Poland)
>> https://easychair.org/cfp/NCL24
>>
>> Why is Minimal Logic at the core of many things?
>> Because it is the logic of Curry-Howard isomorphism
>> for simple types:
>>
>> ----------------
>> Γ ∪ { A } ⊢ A
>>
>> Γ ∪ { A } ⊢ B
>> ----------------
>> Γ ⊢ A → B
>>
>> Γ ⊢ A → B           Δ ⊢ A
>> ----------------------------
>> Γ ∪ Δ ⊢ B
>>
>> And funny things can happen, especially when people
>> hallucinate duality or think symmetry is given, for
>> example in newer inventions such as λμ-calculus,
>>
>> but then omg ~~p => p is nevertheless not provable,
>> because they forgot an inference rule. LoL
>>
>> Recommended reading so far:
>>
>> Propositional Logics Related to Heyting’s and Johansson’s
>> February 2008 - Krister Segerberg
>> https://www.researchgate.net/publication/228036664
>>
>> The Logic of Church and Curry
>> Jonathan P. Seldin - 2009
>> https://www.sciencedirect.com/handbook/handbook-of-the-history-of-logic/vol/5/suppl/C 
>>
>>
>> Meanwhile I am going back to my tinkering with my
>> Prolog system, which even provides a more primitive
>> logic than minimal logic, pure Prolog is minimal
>>
>> logic without embedded implication.
> 

[toc] | [prev] | [standalone]

Page 3 of 3 — ← Prev page 1 2 [3]

Back to top | Article view | sci.math

csiph-web