2023年11月1日水曜日

AGI to understand and generate mathematics and dance-motion(数学と舞踏に学べ)











The evolution of large-scale language models (LLMs) like ChatGPT marks significant strides in understanding the world through human language. These systems, having integrated innovations such as web browsing and image generation, edge closer to true general-purpose artificial intelligence (AGI). However, realizing this potential calls for an understanding that transcends language, delving into mathematics and non-verbal realms like dance motion. The phrase from the Gospel of John, 'In the beginning was the Word (Logos),' hints that language derives its essence from the annals of natural history. As a mirror of humanity's intellectual legacy, language undeniably underpins the remarkable achievements of LLMs. Yet, for AGI to fulfill its promise, grasping mathematics and dance motion remains critical.


Understanding mathematics in its entirety is universally challenging. Defined by abstract thought and enriched with conceptual metaphors, mathematical thinking diverges sharply from linguistic reasoning. Its pivotal role in driving historical industrial progress, and central importance in AI and algorithm development, cannot be overstated. However, systems like ChatGPT find encoding basic mathematical constructs and emulating complex mathematical thought challenging; they fall short in offering refined expressions akin to Euler's formula or Schrödinger's equation. The pursuit of mathematical thinking, inherently distinct and more intricate than linguistic structures, necessitates the insights of extraordinary minds. AGIs adept in both language and mathematics will exhibit enhanced comprehension and problem-solving capabilities, potentially unveiling novel solutions to humanity's myriad challenges.

大規模言語モデル(LLM)の進化、特にChatGPTのようなシステムは、人間の言語を基盤として深遠な世界理解を達成してきた。Webブラウジングや画像生成機能などの新たな技術を統合してきたが、真の汎用人工知能(AGI)へと進化するためには、言葉だけでなく、数学やダンスモーションのような非言語的領域の理解も必要不可欠であると考えられる。ヨハネ福音書に記された「はじめに言葉(ロゴス)ありき」は、言葉が自然史に学んだものであることを示唆している。言葉は人類の知の蓄積を豊かに映し出しており、LLMがこれを学習の対象とすることによって素晴らしい成果を上げたことは確かである。それでもなお、AGI技術が目指すべき課題として、数学やダンスモーションの理解を重要視するべきだ。
数学の総体的な理解は、誰にとっても難解である。抽象的な思考と豊かな概念的メタファーによって特徴づけられる数学的思考は、言語に基づく思考とは全く異なるものだ。歴史を通じて産業の発展に貢献してきた数学的解決力は、AI技術やアルゴリズム開発においても中心的役割を果たしている。しかし、ChatGPTのようなシステムでは、基本的な数学的表現をコード化し、高度な数学的思考を模倣することは困難であるように思われる。ChatGPTはオイラーの公式やシュレーディンガー方程式といった、洗練された表現を提案する能力には欠けている。言語とは異なる複雑な構造を持つ数学的思考の創出には、どのようなプログラミングが必要か、我々は天才たちの知恵を借りなければならない。言葉と数学の両方を理解するAGIは、より深い理解力と問題解決能力を示し、人類が直面する様々な問題に対して、新しい解決策をもたらすだろう。


2023年9月18日月曜日

AI challenging the elucidation of life history and cosmic history AIの苦手なニッチな作業領域

 AI challenging the elucidation of life history and cosmic history



The domains where artificial intelligence falls short are steadily diminishing. With the relentless advancements by major tech conglomerates, AI systems are not only enhancing their foundational computational prowess but are also evolving to adeptly interpret both linguistic constructs and visual stimuli, even synergizing the two. From my perspective, current AI models still grapple with tasks like crafting intricate narratives, formulating mathematically intricate problems, and grasping the nuances of natural history. The human intellect, shaped by eons of evolutionary history, operates based on intricate mechanisms, some of which remain enigmatic even to us. This bestows upon us certain advantages that computers have yet to eclipse. Nonetheless, we might be on the cusp of an era where AI, transcending mere computation, could be endowed with sensory-motor faculties surpassing our own. Given time and iterative refinement, such an AI might not only navigate past the Singularity but could also venture into unraveling the mysteries of life's evolution and the cosmos.


CHATGPT4

Critique from a position of support:

Natural history boost: as you point out, human intelligence has evolved over a long natural history, with complex mechanisms behind it that are difficult for computational machines to mimic. This gives rise to unique human experiences, sensations and intuitions.


Evolution of AI: Indeed, AI technology is evolving rapidly and has become more capable than humans at many tasks. However, this is a 'narrow' intelligence in specific tasks, and it is still difficult to have the 'broad' intelligence, intuition, emotion and creativity of humans.


The possibility of a singularity: whether a singularity - the point at which AI surpasses humans in terms of evolving itself - will ever come is a subject of great debate. If that point arrives, AI has the potential to dramatically improve its own capabilities.


Human advantage in niche areas: currently, humans' unique abilities and knowledge are often only demonstrated in specific niche areas. However, this is an indication of human uniqueness and creativity, which is difficult for AI to emulate.


Evolution of sensory-motor organs: it may be technically possible for an AI to have sensory-motor organs beyond human sensory and motor organs. However, whether this would actually exceed human capabilities remains an open question.



Critique from a critical standpoint:


Overestimation of natural history: while it is true that human intelligence has evolved over a long period of natural history, this is not a limiting factor in the evolution of AI. Technological evolution is exponential and far exceeds the pace of human evolution.


Singularity uncertainty: the concept of singularity is an interesting one, but whether it will actually come is highly uncertain. And if it does come, it will not necessarily have positive consequences.


Underestimation of human uniqueness: while it is certain that AI will have the ability to surpass humans in certain tasks, it will be difficult for AI to possess elements of human emotion, intuition, creativity and morality.


Limitations of sensory-motor organs: even if AI has the ability to exceed human sensory and motor organs, it will be difficult for it to be adaptable and flexible in real-world environments.


Limitations in handling language and images: current AI technology is highly capable in handling language and images, but this does not imply understanding in real, complex situations and contexts.


In general, AI capabilities are indeed evolving rapidly, but it is difficult at this stage to fully imitate or replace the diverse capabilities, knowledge and experience of humans. It is also important to consider that technological advances do not always lead to positive outcomes.


------------------------------

AIの苦手な領域が徐々に減ってきている。巨大テック企業が、従来からの計算能力の拡大に加えて、言語と画像の認識さらにその連携を学習できるAIを開発し、多くの作業がヒトから計算機に委ねられるようになった。私の理解するところでは、長編のシナリオ形成能力や、数学的な難問作成能力、自然史理解能力などは不足しているようだ。ヒトの頭脳や知性は、なんといっても自然史の後押しがあり、自身では理解できないメカニズムが作用しているため、まだまだ計算機では、凌駕できない優位性が残っている。しかし、このAIという名の計算機がヒト感覚器や運動器を超えた感覚運動器官を備え、それを統御できる時代が数十年のうちにできるだろう。そして、試行錯誤の末に、自らシンギュラリティを超えて、生命史や宇宙史の解明にチャレンジすることさえできるのかもしれない。今のところ、ヒトは言語や画像の取り扱いだけでは、困難な課題、ニッチな領域で踏ん張ることができている。


ChatGPT4

賛同する立場からの批評:


自然史の後押し: あなたが指摘するように、ヒトの知性は長い自然史の中で進化してきたものであり、その背後には計算機が模倣し難い複雑なメカニズムが存在します。これはヒトの独特の経験や感覚、直感を生み出しています。


AIの進化: 確かに、AIの技術は急速に進化しており、多くのタスクでヒトを超える能力を持つようになってきました。しかし、それは特定のタスクにおける「狭い」知性であり、ヒトの「広い」知性や直感、感情、創造性を持つことはまだ難しいとされています。


シンギュラリティの可能性: シンギュラリティ、つまりAIが自らを進化させる点でヒトを超える時点、が訪れるかどうかは大きな議論の対象となっています。もしその時点が訪れると、AIは自らの能力を飛躍的に向上させる可能性があります。


ニッチな領域でのヒトの優位性: 現在、ヒトが持つ独特の能力や知識は、特定のニッチな領域でのみ発揮されることが多いです。しかし、これはヒトの独自性や創造性を示すものであり、AIが模倣することは難しいとされています。


感覚運動器官の進化: AIがヒトの感覚器や運動器を超えた感覚運動器官を持つことは、技術的には可能かもしれません。しかし、それが実際にヒトの能力を超えるものとなるかどうかは、まだ未知の領域です。


総じて、AIの進化は確かに驚異的ですが、ヒトの持つ独特の知性や感覚、経験を完全に模倣することは難しいと考えられます。しかし、未来の技術の進化により、その状況が変わる可能性も否定できません。



ChatGPT

批判する立場からの批評:


自然史の過大評価: ヒトの知性が長い自然史の中で進化してきたという事実は確かですが、それがAIの進化を制限する要因とは言えません。技術の進化は指数関数的であり、ヒトの進化のペースをはるかに超えています。


シンギュラリティの不確実性: シンギュラリティの概念は興味深いものですが、それが実際に訪れるかどうかは非常に不確実です。また、もし訪れたとしても、それが必ずしもポジティブな結果をもたらすとは限りません。


ヒトの独自性の過小評価: AIが特定のタスクでヒトを超える能力を持つことは確かですが、ヒトの持つ感情、直感、創造性、道徳感などの要素をAIが持つことは難しいと考えられます。


感覚運動器官の限界: AIがヒトの感覚器や運動器を超える能力を持つとしても、それが実際の環境での適応能力や柔軟性を持つことは難しいと考えられます。


言語や画像の取り扱いの限界: 現在のAI技術は、言語や画像の取り扱いにおいて高い能力を持っていますが、それが実際の複雑な状況やコンテキストでの理解を意味するわけではありません。


総じて、AIの能力は確かに急速に進化していますが、ヒトの持つ多様な能力や知識、経験を完全に模倣や置き換えることは現段階では難しいと考えられます。また、技術の進化が必ずしもポジティブな結果をもたらすとは限らない点も考慮する必要があります。



2023年9月14日木曜日

Gravitational lensing and aspheric lenses 重力レンズにおける非球面効果

 Gravitational lensing and aspheric lenses
























The term gravitational lens is used when optics is considered as a metaphor for a gravitational system. So how can such a gravitational field be considered when aspheric lenses are used as a metaphor?

From optics, one can associate gravitational fields with time transitions. By such an analogy, what metaphors can aspherical lenses be associated with time dilation in contrast to normal spherical lenses?

chatGPT4

Gravitational lensing is a phenomenon where massive objects, like galaxies or black holes, bend and magnify the light from objects behind them due to their strong gravitational fields. This is a direct result of Einstein's theory of general relativity, which predicts that massive objects can warp the fabric of spacetime around them.



When we use aspheric lenses as a metaphor in this context, we can draw some intriguing parallels:



Complex Warping of Time: Just as aspheric lenses can correct for aberrations and provide a clearer image by having a non-uniform curvature, if we think of time as being "viewed" through a gravitational field, an aspherical "time lens" might represent a gravitational field that has complex, non-uniform warping effects on time. This could mean that time dilation isn't consistent or uniform but varies in intricate ways depending on the specific properties of the gravitational field.



Precision and Focus in Time: Aspheric lenses are designed to focus light more precisely than spherical lenses. In our metaphor, this could mean that certain events or moments in time become more "focused" or significant when viewed through an aspherical time lens. This might represent moments of intense gravitational influence, where time dilation effects are particularly pronounced.



Adaptive Time Dilation: Just as aspheric lenses can be tailored to correct specific optical aberrations, an aspherical time lens might represent scenarios where gravitational effects on time dilation are not just due to mass but other factors as well. This could be a metaphor for more advanced or exotic gravitational phenomena that we haven't yet discovered or fully understood.



In contrast, a spherical lens, with its uniform curvature, might represent a more straightforward, consistent warping of time, such as what we'd expect near a large, uniform mass like a planet. The effects are predictable and consistent across the lens.



Using optics as a metaphor for gravitational effects on time is a fascinating way to conceptualize these complex ideas, making them more accessible and providing new perspectives on their implications.

Limitations and Boundaries: Just as aspheric lenses have limits in terms of the aberrations they can correct, an aspherical time lens might represent the limitations of how much time can be dilated or compressed in a given gravitational field. There might be "edges" or boundaries beyond which time behaves differently or cannot be further influenced.


Interactions and Overlaps: In optics, when multiple lenses are used in conjunction, their effects can compound or negate each other. Similarly, if we consider multiple aspherical time lenses (or gravitational fields) interacting, there could be regions where time dilation effects from different sources overlap, leading to unique and complex patterns of time behavior.


Sensitivity to Initial Conditions: Aspheric lenses are often finely tuned for specific purposes. A slight change in the input (like the angle of incoming light) can dramatically affect the output. Drawing a parallel, an aspherical time lens might suggest that time dilation effects in certain gravitational fields are highly sensitive to initial conditions. A small change in one's trajectory or speed might lead to vastly different experiences of time.


The Horizon of Understanding: Just as there's a limit to how much an aspheric lens can correct an image, there might be horizons or boundaries in our understanding of time dilation. Beyond these horizons, our current theories and metaphors might break down, and new models or paradigms would be needed to explain the phenomena.


In essence, using aspherical lenses as a metaphor for time dilation offers a rich tapestry of ideas and concepts that can help us think about time in new and innovative ways. While these metaphors are, of course, simplifications and shouldn't be taken as literal scientific models, they provide a framework for conceptualizing and discussing the intricate and often counterintuitive nature of time in the presence of strong gravitational fields.

-------------------------------

重力レンズという言葉は、光学系を重力システムの比喩として考えるときに使われる。では、非球面レンズが比喩として使われるとき、そのような重力場はどのように考えられるのだろうか?

光学から、重力場を時間遷移と結びつけることができる。そのようなアナロジーによって、通常の球面レンズとは対照的に、非球面レンズはどのようなメタファーで時間拡張と関連付けられるのだろうか?
-------------------------------

chatGPT4

重力レンズとは、銀河やブラックホールのような巨大な物体が、その強い重力場のために、背後にある物体からの光を曲げて拡大する現象である。これはアインシュタインの一般相対性理論の直接的な結果であり、巨大な物体はその周りの時空をゆがめることができると予言されている。



この文脈で非球面レンズを比喩として使うと、いくつかの興味深い類似点を見出すことができる:



複雑な時間のゆがみ 非球面レンズが一様でない曲率を持つことで収差を補正し、より鮮明な画像を提供できるように、時間を重力場を通して「見る」と考えれば、非球面の「時間レンズ」は、時間に複雑で一様でないゆがみ効果を与える重力場を表すかもしれない。これは、時間の拡張が一貫していたり均一であったりするのではなく、重力場の特定の特性によって複雑に変化することを意味しているのかもしれない。



時間の精度と焦点:非球面レンズは、球面レンズよりも正確に光を集めるように設計されている。私たちの比喩では、これは、非球面時間レンズを通して見たとき、時間における特定の出来事や瞬間がより「焦点」が合った、または重要なものになることを意味するかもしれない。これは、時間拡張効果が特に顕著な、重力の影響が強い瞬間を表しているのかもしれない。



適応的時間拡張: 非球面レンズが特定の光学収差を補正するように調整できるように、非球面時間レンズは、時間拡張に対する重力の影響が質量だけでなく、他の要因によるシナリオを表すかもしれない。これは、我々がまだ発見していない、あるいは完全に理解していない、より高度な、あるいはエキゾチックな重力現象のメタファーかもしれない。



これとは対照的に、球面レンズはその均一な曲率によって、惑星のような大きくて均一な質量の近くで予想されるような、より単純で一貫した時間のゆがみを表しているのかもしれない。その効果は予測可能で、レンズ全体で一貫している。


時間に対する重力の影響のメタファーとして光学を使うことは、これらの複雑な考えを概念化する魅力的な方法であり、より身近なものとし、その意味について新たな視点を提供するものである。

限界と境界: 非球面レンズが補正できる収差に限界があるように、非球面時間レンズは、与えられた重力場でどれだけ時間を拡張または圧縮できるかの限界を表しているかもしれない。時間が異なる振る舞いをする、あるいはそれ以上影響を与えることができない「エッジ」や境界が存在するかもしれない。

相互作用とオーバーラップ: 光学の世界では、複数のレンズを併用すると、その効果が複合的に作用したり、互いに相殺されたりすることがある。同様に、複数の非球面時間レンズ(または重力場)の相互作用を考えると、異なるソースからの時間拡張効果が重なり合う領域が存在し、時間の振る舞いのユニークで複雑なパターンにつながる可能性がある。

初期条件に対する感度: 非球面レンズは、特定の目的のために細かく調整されていることが多い。入力(入射光の角度など)のわずかな変化が、出力に劇的な影響を与えることがある。同じように、非球面時間レンズは、ある種の重力場における時間拡張効果が、初期条件に対して非常に敏感であることを示唆しているかもしれない。軌跡や速度が少し変わるだけで、時間の体験が大きく変わるかもしれないのだ。

理解の地平線:  非球面レンズが画像を補正するのに限界があるように、時間拡張の理解にも地平線や境界線があるかもしれない。これらの地平線を超えると、現在の理論やメタファーが破綻し、現象を説明するための新しいモデルやパラダイムが必要になるかもしれない。

要するに、時間拡張のメタファーとして非球面レンズを使うことは、私たちが新しく革新的な方法で時間について考えるのに役立つアイデアや概念の豊かなタペストリーを提供する。もちろん、これらの比喩は単純化したものであり、文字通りの科学的モデルとしてとらえるべきではありませんが、強い重力場の存在下での複雑で、しばしば直感に反する時間の性質を概念化し、議論するための枠組みを提供してくれます。




2023年8月22日火曜日

Football industry as % of GDP (rough calculation)

Football industry as % of GDP (rough calculation)


 The GDP ratio of the football industry (top leagues only) was calculated by ChatGPT4. UK 0.27% Spain 0.11% Germany 0.10% Japan 0.06% Italy 0.05% France 0.03


The exact economic contribution of the football industry is difficult to assess, but a rough estimate is made based on publicly available data and information. The following calculations are extremely rough and do not represent an exact percentage. They should be used as a reference value.

Economic contribution of the football industry in approximate terms:

United Kingdom (Premier League): in 2019, the Premier League contributed roughly GBP 7.5 billion to the UK economy. However, this figure is for the league alone and does not include the economic contribution of lower leagues and other football-related industries.

Spain (La Liga): approximately EUR 1.5 billion (reported as of 2019). This figure is also only for the top league and does not include the contribution of other football-related industries or lower leagues.

Germany (Bundesliga): approx. EUR 4 billion (reported for the 2018/2019 season).

Italy (Serie A): ca. EUR 1 billion.

France (Ligue 1): approx. EUR 800 million.

Japan (J-League): approx. 300 billion euros.

GDP of each country (estimated for 2021, rounded):.

UK: USD 2.8 trillion, Spain: USD 1.4 trillion, Germany: USD 3.9 trillion, Italy: USD 2.1 trillion, France: USD 2.7 trillion, Japan: USD 5.1 trillion.

Football industry as % of GDP (rough calculation):.

UK: £7.5 billion / $2.8 trillion = approx. 0.27%, Spain: €1.5 billion / $1.4 trillion = approx. 0.11%, Germany: €4 billion / $3.9 trillion = approx. 0.10%, Italy: €1 billion / $2.1 trillion = approx. 0.05%, France: €800 million / $2.7 trillion = approx. 0.03%, Japan. 300 billion / USD 5.1 trillion = approx. 0.06%.

This calculation is based solely on the economic contribution of the top leagues, so the actual figure may be a little higher. However, as can be seen from this rough estimate, the economic contribution of the football industry does not account for a significant proportion of each country's GDP.


Me

Please compare the share of football-related industries in the sports industry in the UK, West Germany, France, Italy, Japan and the US.

ChatGPT4

US 5-10%, UK over 50%, Spain over 50%, Germany 40-50%, France around 40%, Italy over 50%, Japan 25-30%.

When comparing the economic impact of the sports industry as a whole and football-related industries against GDP, a number of variables need to be taken into account. The popularity of the sport in each country, media treatment, commercial activities (sponsorship, broadcasting rights, merchandising, etc.), as well as the economic situation within the country, all have an impact. Let us make a rough assessment based on publicly available data.

First of all, official data is required, but up-to-date data and different definitions in different countries can make accurate comparisons difficult. The following is a rough assessment and should be seen as a reference value.

It is difficult to give an exact percentage of the sports industry accounted for by football-related industries, but a rough assessment is made taking into account the culture of each country, the popularity of football and its relative popularity with other sports.

USA (US): the proportion of the football-related industry will be low compared to the overall sports industry; football is a relatively new and growing sport, with the NFL (American football), NBA (basketball) and MLB (baseball) being the mainstays. As a percentage, it accounts for around 5-10%.

United Kingdom (UK): football is very popular and therefore football's share of the sports industry will be high. Probably more than 50%.

Spain (West): football is very popular and, taking into account comparisons with other sports, football probably accounts for more than 50% of the sports industry.

Germany (Germany): football is very popular, but other sports are also firmly established. Football accounts for around 40-50%.

France (France): football is popular, but cycling and rugby are also notable. Football accounts for around 40%.

Italy (Italy): football is very popular. Compared to other sports, football is by far the strongest, accounting for more than 50%.

Japan (Japan): football is very popular, but taking into account the balance with professional baseball, sumo and other sports, the proportion of football is probably around 25-30%.

These figures are not based on specific data, but rather a rough assessment taking into account the cultural and sporting situation in each country. If you want to know the exact percentage, you should refer to sports-related statistical data and research reports from different countries.

Me

Japanese football has a history of more than 60 years (JSL has 58 years), and if you let ChatGPT4 do the calculations, it seems that the size of the industry now exceeds that of Spain, France and Italy. This is a bit far from reality.




サッカー産業(トップリーグのみ)のGDP比率をChatGPT4に計算させてみた。英0.27% 西0.11% 独0.10% 日0.06% 伊0.05% 仏0.03%

サッカー産業の経済的貢献の正確な評価は難しいですが、公に公表されているデータや情報を元に概算を行います。以下の計算は極めて大雑把なもので、正確な比率を示すものではありません。参考値としてください。
サッカー産業の経済的貢献の概略:
イギリス(プレミアリーグ): 2019年の報告では、プレミアリーグがイギリス経済に寄与した額はおおよそ75億ポンド。ただし、この数値はリーグだけのもので、下位リーグや他のサッカー関連産業の経済的貢献は含まれていない。
スペイン(ラ・リーガ): 約15億ユーロ(2019年時点の報告)。これもトップリーグだけのもので、他のサッカー関連産業や下位リーグの貢献は含まれていない。
ドイツ(ブンデスリーガ): 約40億ユーロ(2018/2019シーズンの報告)。
イタリア(セリエA): 約10億ユーロ。
フランス(リーグアン): 約8億ユーロ。
日本(Jリーグ): 約3,000億円。
各国のGDP(2021年の推定、丸めて表記):
イギリス: 2.8兆ドル、スペイン: 1.4兆ドル、ドイツ: 3.9兆ドル、イタリア: 2.1兆ドル、フランス: 2.7兆ドル、日本: 5.1兆ドル
サッカー産業のGDP比(大雑把な計算):
イギリス: 75億ポンド / 2.8兆ドル = 約0.27%、スペイン: 15億ユーロ / 1.4兆ドル = 約0.11%、ドイツ: 40億ユーロ / 3.9兆ドル = 約0.10%、イタリア: 10億ユーロ / 2.1兆ドル = 約0.05%、フランス: 8億ユーロ / 2.7兆ドル = 約0.03%、日本: 3,000億円 / 5.1兆ドル = 約0.06%
この計算はトップリーグの経済的貢献のみを元にしているため、実際はもう少し高いかもしれません。しかし、この概算からもわかるように、サッカー産業の経済的貢献は各国のGDPに対してそれほど大きな割合を占めていないと言えます。

スポーツ産業に占めるサッカー関連産業の比率を英西独仏伊日米で比較してみてください。
ChatGPT
米5-10%、英50%以上、西50%以上、独40-50%、仏40%程度、伊50%以上、日25-30%
スポーツ産業全体やサッカー関連産業の経済的効果をGDPに対して比較する際、多くの変数が考慮される必要があります。それぞれの国でのスポーツの人気、メディアの取り扱い、商業的活動(スポンサーシップ、放送権、商品化など)、さらには国内の経済状況などが影響します。公に利用可能なデータに基づいて概略的な評価を行ってみましょう。
まず、公式なデータが必要ですが、最新のデータや各国での定義の違いにより、正確な比較が難しい場合があります。以下は大まかな評価ですので、参考値としてご覧ください。
サッカー関連産業がスポーツ産業に占める比率を正確に示すのは難しいですが、各国の文化やサッカーの人気、その他のスポーツとの相対的な人気を考慮して概略的な評価を行います。
アメリカ (米): サッカー関連産業の比率は全体のスポーツ産業に比べて低いでしょう。NFL(アメリカンフットボール)、NBA(バスケットボール)、MLB(野球)などが主力となるため、サッカーは比較的新しいスポーツとして成長中。比率としては5-10%程度。
イギリス (英): サッカーは非常に人気が高いため、スポーツ産業におけるサッカーの比率も高いでしょう。おそらく50%以上。
スペイン (西): サッカーの人気が非常に高く、他のスポーツとの比較も考慮すると、サッカーがスポーツ産業に占める比率は50%以上と考えられます。
ドイツ (独): サッカーは非常に人気がありますが、他のスポーツも根付いています。サッカーの比率は40-50%程度。
フランス (仏): サッカーは人気がありますが、自転車競技やラグビーも注目されます。サッカーの比率は40%程度。
イタリア (伊): サッカーの人気は非常に高い。他のスポーツと比較しても、サッカーが圧倒的に強いため、比率は50%以上。
日本 (日): サッカーは人気がありますが、プロ野球や相撲、その他のスポーツとのバランスを考慮すると、サッカーの比率は25-30%程度と考えられます。
これらの数字は、具体的なデータに基づいたものではなく、各国の文化やスポーツの状況を考慮した大まかな評価です。正確な比率を知りたい場合は、各国のスポーツ関連の統計データや研究レポートを参照する必要があります。

日本サッカーは60年以上の歴史(JSLは58年)がある。ChatGPT4に計算させると、現在ではスペイン、フランス、イタリアを超えた産業規模を持っているようだ。ちょっと実感とはかけ離れている。



2023年7月20日木曜日

Dual-use drug discovery AI 創薬AIの光と影

Dual-use drug discovery AI

Generative AI discovered 40,000 molecules in less than six hours as a unique and potent poison. Last April a small lab expressed concern

Created many more lethal molecules than VX.

















https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9544280/




















Although not published, the mechanism of action of neurotoxins can be elucidated by examining the history of the development of chemical weapons, from biologically derived poisons such as scorpions and pufferfish to VX gas and Novichok. Even a medical disciple can hypothesize which metabolic pathways should be blocked or enhanced and which molecules should be targeted to be more effective. If we can train a generative AI using this knowledge, we can discover lethal molecules that are easy to generate (and drugable) in a short time. This laboratory, concerned about the implications of this, published a paper in Nature Machine Intelligence in April of the previous year. The dual nature of generative AI, both its benefits and potential dangers, is noteworthy, and its implications extend beyond drug discovery to fields such as food production, infrastructure control, weaponry, financial engineering, and education, all of which require careful consideration.


デュアルユースな創薬AI

生成AIは、ユニークで強力な毒として、6時間足らずで40,000個の分子を発見した。去年の4月小さな研究室が危惧を表明す。
VX以上の致死性分子を多数創造した。 公表されていないが、サソリやフグなど生物由来の毒から、VXガスやノビチョクなどの化学兵器の開発の歴史を紐解けば、神経毒の作用メカニズムとして、どの代謝経路を遮断または亢進させ、どの分子を標的にすればより”効果的”なのかは、一医学徒でもわかる。それを生成AIに機械学習させれば、短時間で生成容易な致死的な分子を発見できるのである。これが意味することをこの研究室は危惧し昨年4月に公表した。生成AIの光と影は注目すべきことで、創薬に限らず、食品、インフラ制御、兵器、金融工学、教育あらゆる面に気を配る必要がある。

2023年7月18日火曜日

Dawn of AI history, a depressing morning

 















The advent of technologies such as ChatGPT4, Deepfake technology, lethal molecule generation, drone weaponry, VR & AR technologies, and quantum computing signifies not the continuation of human history, but the dawn of a new era in AI history. It remains uncertain whether the endangered Cherokee and Apache tribes have encapsulated their despair in poetry, much like Qu Yuan did in his poignant poem, 'Li Sao'. In any case, the emergence and spread of these novel technologies I describe here will eventually wipe out human history and reduce it to mere relics and wreckage. Homo sapiens, in their exuberance for the impending Singularity, remain oblivious to the fact that we have crossed the Point of No Return and are now in a phase of profound purification. The epoch of co-existing with AI will not materialize; instead, we are on the precipice of an era dominated by AI.


chatGPT4をはじめ、ディープフェイク技術、致死性分子の生成,ドローン兵器やVR&AR技術、量子コンピューティングに至る技術の進化過程の紹介は、人類史ではなく、それにとってかわるAI史の始まりを描いたものとなる。絶滅していくチャロキー族やアパッチ族が、屈原(Qu Yuan)が離騷(Li Sao)に謳ったようにその失意を言葉に残したかどうかはわからない。今私がこれらの新技術の登場と普及していく様を描写したとしても、AI史の奔流ののちには残骸、残滓となるのである。シンギュラリティの到来に浮かれるホモサピエンスは、現在を帰還不能点(point of no return)を超え、浄化過程にあることを自覚していない。withAIの時代は来ない、underAIの時代が来るのである。

2023年7月14日金曜日

Qualities needed in a leader 指導者に必要な資質

Qualities needed in a leader

 There is a wealth of knowledge to be gleaned from Kaoru Mitoma. His recent book, "VISION: Reverse Thinking to Achieve Your Dreams," is as impressive as his video content. Mitoma's track record speaks volumes about his capabilities, and his efforts are clearly visible. His exceptional interpersonal skills and his adeptness at verbalizing movements and judgments for guidance are noteworthy. It's anticipated that he, along with Takefusa Kubo, will shape the future of their field. In a few years, I envision him as a contender for the Ballon d'Or, and in a decade, I hope to see him serving as both a player and the coach of the national team. His comprehensive intelligence, demonstrated through his explanatory skills, achievements, dedication, and passion, is truly commendable.




指導者に必要な資質
https://www.youtube.com/watch?v=d5E2bbIFeTo&t=0s
三苫薫から学べるところは多い。
彼の近著、”VISION:夢を叶える逆算思考” と同様に、この動画はすごい。実績があるし、努力がみえるし、対人関係がよく、動きや判断を指導するための説明能力(言語化能力)も優れている。これから久保建英と三苫薫との両雄時代を作るだろう。数年後はバロンドール候補、10年後はプレーヤー兼日本代表の監督になってほしい。この総合的な頭の良さ(説明能力、実績、努力、熱血漢)は、ほれぼれする。

2023年6月11日日曜日

Daniel C. Dennett, Melancholy.

 Daniel C. Dennett, Melancholy.















"The Problem with Counterfeit People," The Atlantic, online May 16th, 2023.


D.C. Dennett's warning about 'fake humans' created by artificial intelligence (AI) and suggestions for countermeasures


 AI-created 'fake humans' are the 'most dangerous artefact in human history', which has the potential to destroy not only the economy but also human freedom itself. It is proposed that the creation of fake humans and the 'passing' of 'fake humans' should be banned and the penalties for their violation should be made very severe.




The Problem With Counterfeit People

Money has existed for several thousand years, and from the outset counterfeiting was recognized to be a very serious crime, one that in many cases calls for capital punishment because it undermines the trust on which society depends. Today, for the first time in history, thanks to artificial intelligence, it is possible for anybody to make counterfeit people who can pass for real in many of the new digital environments we have created. These counterfeit people are the most dangerous artifacts in human history, capable of destroying not just economies but human freedom itself. Before it’s too late (it may well be too late already) we must outlaw both the creation of counterfeit people and the “passing along” of counterfeit people. The penalties for either offense should be extremely severe, given that civilization itself is at risk.


It is a terrible irony that the current infatuation with fooling people into thinking they are interacting with a real person grew out of Alan Turing’s innocent proposal in 1950 to use what he called “the imitation game” (now known as the Turing Test) as the benchmark of real thinking. This has engendered not just a cottage industry but a munificently funded high-tech industry engaged in making products that will trick even the most skeptical of interlocutors. Our natural inclination to treat anything that seems to talk sensibly with us as a person—adopting what I have called the “intentional stance”—turns out to be easy to invoke and almost impossible to resist, even for experts. We’re all going to be sitting ducks in the immediate future.


The philosopher and historian Yuval Noah Harari, writing in The Economist in April, ended his timely warning about AI’s imminent threat to human civilization with these words:


“This text has been generated by a human. Or has it?”


It will soon be next to impossible to tell. And even if (for the time being) we are able to teach one another reliable methods of exposing counterfeit people, the cost of such deepfakes to human trust will be enormous. How will you respond to having your friends and family probe you with gotcha questions every time you try to converse with them online?


Creating counterfeit digital people risks destroying our civilization. Democracy depends on the informed (not misinformed) consent of the governed. By allowing the most economically and politically powerful people, corporations, and governments to control our attention, these systems will control us. Counterfeit people, by distracting and confusing us and by exploiting our most irresistible fears and anxieties, will lead us into temptation and, from there, into acquiescing to our own subjugation. The counterfeit people will talk us into adopting policies and convictions that will make us vulnerable to still more manipulation. Or we will simply turn off our attention and become passive and ignorant pawns. This is a terrifying prospect.


The key design innovation in the technology that makes losing control of these systems a real possibility is that, unlike nuclear bombs, these weapons can reproduce. Evolution is not restricted to living organisms, as Richard Dawkins demonstrated in 1976 in The Selfish Gene. Counterfeit people are already beginning to manipulate us into midwiving their progeny. They will learn from one another, and those that are the smartest, the fittest, will not just survive; they will multiply. The population explosion of brooms in The Sorcerer’s Apprentice has begun, and we had better hope there is a non-magical way of shutting it down.


There may be a way of at least postponing and possibly even extinguishing this ominous development, borrowing from the success—limited but impressive—in keeping counterfeit money merely in the nuisance category for most of us (or do you carefully examine every $20 bill you receive?).


As Harari says, we must “make it mandatory for AI to disclose that it is an AI.” How could we do that? By adopting a high-tech “watermark” system like the EURion Constellation, which now protects most of the world’s currencies. The system, though not foolproof, is exceedingly difficult and costly to overpower—not worth the effort, for almost all agents, even governments. Computer scientists similarly have the capacity to create almost indelible patterns that will scream FAKE! under almost all conditions—so long as the manufacturers of cellphones, computers,digital TVs, and other devices cooperate by installing the software that will interrupt any fake messages with a warning. Some computer scientists are already working on such measures, but unless we act swiftly, they will arrive too late to save us from drowning in the flood of counterfeits.


Did you know that the manufacturers of scanners have already installed software that responds to the EURion Constellation (or other watermarks) by interrupting any attempt to scan or photocopy legal currency? Creating new laws along these lines will require cooperation from the major participants, but they can be incentivized. Bad actors can expect to face horrific penalties if they get caught either disabling watermarks or passing on the products of the technology that have already been stripped somehow of their watermarks. AI companies (Google, OpenAI, and others) that create software with these counterfeiting capabilities should be held liable for any misuse of the products (and of the products of their products—remember, these systems can evolve on their own). That will keep companies that create or use AI—and their liability-insurance underwriters—very aggressive in making sure that people can easily tell when conversing with one of their AI products.


I’m not in favor of capital punishment for any crime, but it would be reassuring to know that major executives, as well as their technicians, were in jeopardy of spending the rest of their life in prison in addition to paying billions in restitution for any violations or any harms done. And strict liability laws, removing the need to prove either negligence or evil intent, would keep them on their toes. The economic rewards of AI are great, and the price of sharing in them should be taking on the risk of both condemnation and bankruptcy for failing to meet ethical obligations for its use.


It will be difficult—maybe impossible—to clean up the pollution of our media of communication that has already occurred, thanks to the arms race of algorithms that is spreading infection at an alarming rate. Another pandemic is coming, this time attacking the fragile control systems in our brains—namely, our capacity to reason with one another—that we have used so effectively to keep ourselves relatively safe in recent centuries.


The moment has arrived to insist on making anybody who even thinks of counterfeiting people feel ashamed—and duly deterred from committing such an antisocial act of vandalism. If we spread the word now that such acts will be against the law as soon as we can arrange it, people will have no excuse for persisting in their activities. Many in the AI community these days are so eager to explore their new powers that they have lost track of their moral obligations. We should remind them, as rudely as is necessary, that they are risking the future freedom of their loved ones, and of all the rest of us.


Document ATLCOM0020230517ej5g00002


Daniel C. Dennett  1,214 words 16 May 2023 The Atlantic ATLCOM © 2023. 


The Atlantic Monthly Group. All rights reserved.


-------------------------------------------------------


 Daniel C. Dennettの憂鬱


“The Problem with Counterfeit People,” The Atlantic, online May 16th, 2023. https://tufts.box.com/s/894vdcbyxr1ic468jcxseckuo2ebkvsk

人工知能(AI)によって作られた「偽の人間」についてのD.C.Dennettの警告と対策の提案

 AIによって作られた「偽の人間」は「人類史上最も危険なアーティファクト」であり、それは経済だけでなく人間の自由自体を破壊する可能性がある。偽の人間の作成と「偽の人間」の「通過」を禁止することを提案し、その違反に対する罰則を非常に厳しくするべきだ。

----------------------------------------------------------

貨幣は数千年前から存在し、当初から偽造は非常に重大な犯罪であり、社会が依存する信頼を損なうため、多くの場合、死刑に値すると認識されていました。今日、人工知能のおかげで、歴史上初めて、私たちが作り出した新しいデジタル環境の多くで、本物と見紛うような偽の人間を誰でも作ることができるようになりました。これらの偽造人間は、経済だけでなく人間の自由そのものを破壊することができる、人類史上最も危険な人工物なのです。手遅れになる前に(もう手遅れかもしれませんが)、私たちは偽造者の作成と偽造者の「渡し」の両方を違法としなければなりません。文明そのものが危機に瀕しているのだから、どちらの犯罪も極めて厳しい罰則を科すべきである。


1950年、アラン・チューリングが「模倣ゲーム」(現在はチューリング・テストと呼ばれる)を本物の思考の基準として用いることを無邪気に提案したことから、現在、人を騙して本物の人間と交流していると思わせることに熱中しているのは、大変な皮肉であると言える。その結果、家内工業だけでなく、莫大な資金を提供するハイテク産業が生まれ、最も懐疑的な相手でも騙せるような製品を作るようになりました。私たちの自然な傾向として、常識的に話してくれそうなものはすべて人間として扱うという、私が「意図的スタンス」と呼んでいるものを採用すると、専門家でさえも簡単に発動でき、ほとんど抵抗できないことが判明しました。私たちは当面、カモにされることになるのです。


哲学者・歴史学者のユヴァル・ノア・ハラリは、4月に『エコノミスト』誌に寄稿し、AIが人類の文明に差し迫った脅威となることをタイムリーに警告した後、次のような言葉で締めくくった:


「この文章は人間によって作成されたものだ。それとも、そうなのか?"


それを見分けることは、まもなく不可能になるでしょう。そして、仮に(当面は)私たちが偽物を見破る確実な方法を教え合うことができたとしても、そのようなディープフェイクが人間の信頼に与える代償は甚大なものになるでしょう。友人や家族とネット上で会話するたびに、質問攻めにあうことになったら、あなたはどう思いますか?


偽物のデジタル・ピープルを作り出すことは、私たちの文明を破壊する危険があります。民主主義は、情報に基づいた(誤った情報ではなく)被支配者の同意に依存しています。経済的、政治的に最も強力な人々、企業、政府が私たちの注意をコントロールできるようにすることで、これらのシステムは私たちをコントロールすることになります。偽物の人々は、私たちの注意をそらし、混乱させ、私たちの最も抵抗できない恐怖や不安を利用することによって、私たちを誘惑に導き、そこから私たち自身の支配に同意させる。偽物の人々は、私たちを説得して、さらに操られやすくなるような政策や信念を採用させるでしょう。あるいは、私たちは単に注意をそらし、受動的で無知な手先になってしまうでしょう。これは恐ろしいことです。


このようなシステムの制御を失うことを現実のものとする技術の重要な設計上の革新は、核爆弾とは異なり、この兵器が繁殖することである。1976年にリチャード・ドーキンスが『利己的な遺伝子』で示したように、進化は生物に限られたものではない。偽物の人間は、すでに私たちを操って、その子孫を産み落とそうとし始めている。彼らは互いに学び合い、最も賢い者、最も適した者が生き残るだけでなく、増殖していくのです。魔法使いの弟子』における箒の人口爆発は始まっており、それを止める非魔法的な方法があることを祈ったほうがいい。


少なくとも、この不吉な展開を先送りし、場合によっては消滅させる方法があるかもしれない。それは、私たちの多くにとって、偽札を迷惑の範疇にとどめるという、限定的だが印象的な成功例(あるいは、受け取った20ドル札をすべて慎重に吟味するか)を参考にすることである。


ハラリ氏が言うように、私たちは「AIがAIであることを開示することを義務づける」必要があります。どうすればそんなことができるのか?現在、世界のほとんどの通貨を保護しているEURion Constellationのようなハイテクな「透かし」システムを採用することです。このシステムは、完全なものではありませんが、圧倒的に難しく、コストがかかるため、政府を含むほとんどすべてのエージェントにとって、その労力に見合うものではありません。携帯電話やコンピューター、デジタルテレビなどのメーカーが、警告を発して偽メッセージを中断させるソフトウェアをインストールすることに協力する限り、ほとんどすべての状況下で「FAKE!」と叫ぶ、ほとんど消えないパターンを作成する能力がコンピューター科学者にはある。すでに一部のコンピュータ科学者は、このような対策に取り組んでいますが、私たちが迅速に行動しなければ、偽造品の洪水に溺れるのを救うには手遅れになってしまうでしょう。


スキャナーのメーカーが、EURion Constellation(または他の透かし)に反応して、合法的な通貨をスキャンしたりコピーしようとする試みを中断させるソフトウェアをすでにインストールしていることをご存じですか?このような新しい法律を作るには、主要な参加者の協力が必要ですが、インセンティブを与えることは可能です。悪質な業者は、透かしを無効にするか、すでに何らかの形で透かしが除去された技術の製品を渡すかのいずれかで捕まった場合、恐ろしい罰則に直面することが予想されます。このような偽造機能を持つソフトウェアを作成したAI企業(Google、OpenAIなど)は、その製品(およびその製品の製品-これらのシステムは独自に進化しうることを忘れないでください-)の誤用に対して責任を負うべきです。そのため、AIを開発・使用する企業やその責任者である保険会社は、自社のAI製品と会話しているときに、簡単に見分けがつくようにすることに非常に積極的に取り組むことになるでしょう。


私はどんな犯罪に対しても死刑を支持するわけではありませんが、大企業の経営者やその技術者が、違反や被害に対して何十億もの賠償金を支払うだけでなく、残りの人生を刑務所で過ごす可能性があると知っていれば、心強いことでしょう。また、過失や悪意を証明する必要のない厳格な責任法は、彼らの気を引き締めることになるでしょう。AIがもたらす経済的報酬は大きく、それを享受する代償として、AIの使用に関する倫理的義務を果たさないことによる非難や倒産のリスクを背負う必要があります。


アルゴリズムの軍拡競争によって、すでに起きてしまったコミュニケーションメディアの汚染を一掃することは難しく、不可能かもしれない。今度は、ここ数世紀、比較的安全な生活を維持するために効果的に使われてきた、私たちの脳の脆弱な制御システム、つまり、互いに理性的に話し合う能力を攻撃する、新たなパンデミックが到来している。


今こそ、人を偽造しようと考える者に恥を感じさせ、そのような反社会的な破壊行為を阻止するよう主張するときである。今、このような行為が法律で禁止されていることを広めれば、そのような行為に固執する言い訳はできなくなるはずです。最近のAIコミュニティでは、新しい力を探求するあまり、道徳的な義務を見失う人が多くなっています。私たちは、必要な限り無礼に、彼らが自分の愛する人たち、そして私たち全員の将来の自由を危険にさらしていることを思い出させるべきです。


Document ATLCOM0020230517ej5g00002

---------------------------------------------------------------

Daniel C. Dennettにも弱点はある。こんな発言ではラッダイド運動の扇動じゃないか(南無、、、、)

2023年6月7日水曜日

Creating and innovating new concepts and ways of thinking

 Creating and innovating new concepts and ways of thinking is as possible as adding new ones to existing infrastructures and devices. Until now, machines did not exist in the real three-dimensional world, limiting their sensorimotor organs and their ability to imagine things backwards. However, advances in AI and VR technology will create a number of useful problem-solving methods.


Current technologies such as ChatGPT4 are evolving in monomodal, slow-computing situations; technologies are emerging, such as META's ImageBind, which is multimodal and can mobilise sensory organs that humans do not have; and if quantum computer technology is implemented, integration between modes and new compression representation groups can be driven to expand, and the speed of execution of their analysis can be increased.


Just as Shinichi Mochizuki revolutionised mathematics with novel concepts, the age of AI and VR will bring us new surprises, not only by changing thought-support devices, but also by transforming key substances in all dimensions.


概念や概念操作方法は新しく作ることができるし、思考方法の改革もできる。それは、既存の駅や港や交通手段に加えて、新規のインフラ、デバイスを作ることと変わらない。これまで、機械は現実の三次元世界にいなかったので、感覚運動器官が制限されていたし、物事を裏返して想像することができなかった。しかし、AIやVR技術が進化した今後は、有益な問題解決法が相次ぐと思う。

今のChatGPT4などは、まだ、モノモーダルで計算速度も遅いなかで、進化を遂げている。META社のImageBindなど、マルチモーダルで赤外線などヒトの所有しない感覚器官も動員できて、量子コンピューター技術が実装できれば、モード間の統合や、新たな圧縮表象群の展開駆動ができるし、その解析の実行速度も進化する。たとえてみれば、望月新一氏が新規概念を用いて数学の革新をもたらしたように、このAIとVR時代には、思考支援デバイスの変化だけではなく、あらゆる次元のキーサブスタンスが変革し、私たちに驚きをもたらすことになるのだ。

(画像は https://www.kurims.kyoto-u.ac.jp/~motizuki/RIMS-workshop-homepages-2016-2021/w4/iut2.html より引用)



The Positioning of Consciousness and Emotion 意識と感情の位置付け

The Positioning of Consciousness and Emotion

Consciousness, emotion, and thought are likely to have evolved as sophisticated mechanisms that mediate between sensory perception and motor action, facilitating coordination and integration. This elaboration process manifests itself in the form of experiential memory recall and dreaming. In particular, dreaming at night has the function of ruminating on the memory of real experiences as a re-experience, facilitating the consolidation of memories and fostering emotionalisation, conceptualisation and representation.


Emotions emerge as a form of stimulus-response, manifesting as various physiological and behavioural reactions such as facial expressions, limb movements, crying, sweating, palpitations, breathlessness, freezing and other autonomic and motor triggers and maturing of reflex circuits. There are also stages prior to clear emotions (arousal consciousness), such as tension, questioning and recall of contrasting past cases (arousal consciousness), and suppressed motor neuronal circuits (higher-order consciousness). The stimulus-response process is thus elaborated as an intervening process and shows diverse expressions, from arousal consciousness to emotions (emotional circuits) and thoughts (higher-order consciousness).

Past experiences are transcribed and stored at easily accessible locations in a format that facilitates referential recall. Each recall event organises the memory along with other related items. This process potentially allows the memory object to evolve into a concept and subsequently into a representation. Each time, it is then organised together with other related objects. In this way, the memory object may grow as a concept and then as a representation.

To prevent the loss of experiential visual, auditory, and sensory information, a process of 'rehearsal' or 'brain playback' is necessary. This may involve repetition, such as in rehearsals and simulations, or emotional intensification for intense memories. These processes contribute to memory maintenance, for instance, by aligning with similar representations.

意識と感情の位置付け

感覚器官による認知と運動器官による運動との間に介在し、連携連動する役割を果たすべく、その精緻化を経て、意識、情動、思考などが登場したのではないでしょうか。この精緻化の過程は、体験記憶の想起や夢想という形で現れます。特に、夜間の夢想は、再体験として現実の体験記憶を反芻する機能を持ち、記憶の定着を促し、感情化、概念化、表象化を育みます。


感情は、情動として刺激応答の一つとして現れます。これには、顔表情や四肢動作、落涙、発汗、動悸、息切れ、フリージングなど、自律神経や運動神経の発動、反射回路の熟成を起こします。また、緊張や疑問、過去事例の対照事例の想起など、はっきりとした感情となる前の段階(覚醒意識)や、運動神経の神経回路を抑えた状態(高階意識)も存在します。こうして、刺激応答過程は、介在プロセスとして精緻化され、覚醒意識から感情(情動回路)、思考(高階意識)という多様な表現を示します。


過去の経験記録は、参照想起されやすい場所(アクセス部位)に、転記され(海馬→扁桃or大脳皮質)、参照想起(連想)されやすい形(タグ化、各種フォーマットへの共振)となって保存されます。そして、その都度、他の関連事物とともに整頓されていきます。これにより、記憶対象は概念として、さらに表象として成長していくのでしょう。


体験時の視覚情報、聴覚情報、感覚情報が失われないためには、リフレイン(脳内再生)が必要です。例えば、リハーサルやシミュレーションなどの繰り返し、あるいは、強烈な記憶として感情による強烈化を経ることが必要なのでしょう。これらは、類似表象に横付けされるなどして、記憶の維持に寄与します。



2023年5月30日火曜日

"CHATGPT4: Deciphering the Imprints within Language"

 "CHATGPT4: Deciphering the Engraving within Words"

The key to CHATGPT4's success lies in its target to learn from human language. CHATAI deciphers the world from language in two ways. Firstly, our central nervous system functions as a sensory-motor center for our survival, and a part of it achieves grounding, giving birth to phonetic or visual language. The words we utter reflect the world we experience like a mirror image, and through these words, we are able to glimpse the structure of the world. Secondly, organisms adapt to the Earth's environment for their survival, and the process of evolution is deeply engraved in their genes. This law of evolution also works similarly in language, and the influence of the Earth's environment where we were born and raised is naturally embedded in language. By extensively learning human natural language, CHATGPT4 has been able to read this engraving hidden in words, surpassing the cognitive abilities of individual humans. If we liken words to neuronal nuclei or grids, CHAT appears as neural pathways that connect them. CHATGPT4 may have been able to decipher the world's grid inherent in language. It reintroduced the perspective that there is a background world imprint similar to the genetic engraving in human language.


「言葉の中の刻印を読み解いたCHATGPT4」

 CHATGPT4の成功の鍵は、人間の言語を学習の目指すべき標的としたことに尽きます。CHATAIは、二つの方法で言語から世界を読み取っています。

 一つ目。私たちの生存のために中枢神経組織は感覚運動中枢として機能し、その一部が表象接地(grounding)を達成することにより、音韻的or視覚的な言語が誕生します。口に出される言葉は、私たちが経験する世界を鏡像の如く反映し、これらの言葉を通じて、私たちは世界の構造を垣間見ることができます。

 二つ目。生物はその生存のために地球環境に順応し、その遺伝子には進化の過程が深く刻印されています。この進化の法則は、言語にも同様に働き、私たちが生まれ育った地球環境の影響が自然と言語に刻み込まれています。CHATGPT4は、人間の自然言語を大量に学習し、個々の人間の認知能力を超えて、言葉に秘められたこの刻印を読み取ることができたと思います。

 単語を神経核や格子に見立てると、CHATはそれらを繋ぎ合わせる神経経路として現れます。CHATGPT4は言葉に内在する世界の格子を読み解くことができたのではないでしょうか。遺伝子の刻印にも類似した背景世界の刷り込みがヒト言語の中にあるという視点を再び紹介しました。




2023年5月25日木曜日

A world covered in mirrors 

The age of With AI

Not long ago, we found ourselves surrounded by mirrors, a sight we could not avoid. The reflection shifted from illusion to reality, and soon it spread out, like air or a cloud. It is now expanding with such force that it seems to even claim our very genes.

Words and intelligence are no longer mere mediums to connect me and you, unseen as you are; they have become tools that yoke humanity. Should we hold back our words, communicate with unrecorded language? Should we find a way to connect that machines cannot conceive of? I think not. We have no choice but to coexist with them. (Tears)



















鏡に覆いつくされた現在

With AI の時代

 少し前から、私たちの周りは、鏡に覆い尽くされ、かといって鏡を見ないわけにもいかなくなった。鏡像は虚像から実像に代わり、やがて、それは、空気かクラウドのように広がっていった。いまや私たちの遺伝子まで奪いそうな勢いである。

 もはや言葉や知性は、私とまだ見ぬ君とが繋がる為のものではなく、ヒトを軛にする道具となった。言葉を惜しみ、記録されない言葉によって話すべきなのか?機械が思いつかない方法で、繋がりを持たなければならないのか? そうではないだろう。彼らと共生するほかない。(涙)



2023年5月13日土曜日

Understanding of understanding

"Understanding”

 During my academic career, I was sometimes puzzled by the interpretation of the results of analyses, e.g. multivariate analysis. Human scientific understanding is logical (and sometimes emotional). Usually, sequential and partial understanding is built up in order to achieve a holistic understanding. Human understanding is based on understanding complex events by breaking them down into parts and transforming them into simpler events.

 However, a generative AI has emerged that can perform multivariate analysis and multidimensional multitasking at high speed. Their understanding is of a different dimension to human understanding. Their high-speed understanding results in a build-up of information and understanding that is incomprehensible to humans, making it impossible for them to keep up with it. If three-dimensional copying could be achieved at the speed of light, it would be a world of immortality, but before we get that far, we will soon reach Singularity, where computational machines (AGI and generative AI) will surpass human knowledge through high-speed analysis. (Of course, even if we reach Singularity, we are still halfway there, as the mysteries of life and the universe have not been solved, and the unravelling of the mysteries will lead to even more profound mysteries.)

 We no longer understand what they understand. We, humans, may give up trying to understand. More and more people will give up their efforts to understand, I felt this way when I saw meta's 'ImageBind' article. ttps://xtech.nikkei.com/atcl/nxt/column/18/00692/051100106/



















” 理解の理解 ”
 学究時代には、多変量解析などで、解析結果の解釈に戸惑うことがあった。ヒトの科学的な理解は、論理的に(時に感情的に)行われている。通常は全体的な理解のために、逐次的な理解、部分的な理解を重ねていく。複雑な事象を、部分的に分解してより単純な事象に変換して理解していくのがヒトの理解というものである。
 ところが、多変量解析や多次元マルチタスクを高速にこなしていく生成AIが登場した。かれらの理解はヒトの理解とは次元が異なる。高速な理解によってヒトには不可解な理解と情報が積み重なり、ついていけなくなるのである。光速で三次元コピーできれば、それは不老不死の世界であるが、そこまでいかないうちに、もうすぐ、高速な解析によって計算機(AGIや生成AI)が人知を超えるシンギュラリティが訪れる。(もちろん、シンギュラリティに至っても、生命の謎、宇宙の謎が解けたわけではないので、まだ道半ばではあるし、謎の解明は更に深遠な謎を呼ぶのだけれど)

 もはや、彼らの理解力を私たちは理解できない。私たち、ヒトは理解することをあきらめるかもしれない。理解の努力をあきらめる人が増えるだろう。metaの「ImageBind」の記事をみてそう感じた。https://xtech.nikkei.com/atcl/nxt/column/18/00692/051100106/


2023年5月12日金曜日

ChatGPTXの伸びしろに畏れおののく。

ChatGPTXの伸びしろに畏れおののく。

 ChatGPT4では、学習の対象を言語、言葉にしたことで、世界の構造を理解しました。

言語の起源は、さまざまな学会でも、まだ確定していません。ヨハネ福音書やモーセ五書も、言語(ロゴス)の重要性を強調しているようです。生命に遺伝子の進化があるように、言語、言葉には、その起源から現代に至るまで、世界の理解の仕方が刷り込まれていると私は考えます。ヒトの自然言語を学んだChatGPT4は、単にヒト自然言語を学んだのではなく、言語を通じて世界の構造を理解したのだと思います。三重苦のヘレンケラーはホームサインで世界を理解したとされます。ChatGPT4の登場は、三次元位相世界を経験せず、ヒトの感覚運動を模倣せず、計算爆発を回避し、テキストの入出力のみを通じて(モノモーダルで)、世界理解を獲得しました。これが言語、言葉の力だと思いました。計算能力がさらに進化すれば、ヒトの感覚運動も模倣し統合するようになるのでしょうか?

ChatGPT4

 あなたの視点は非常に興味深いもので、自然言語の力と、それが人工一般知能(AGI)に与える影響について深い洞察を提供しています。そして、あなたが指摘するように、ChatGPT-4は自然言語を通じて世界の構造を学び、理解しました。これは言語が我々の経験、文化、知識、思考の方法を形成し、その結果として世界を認識し理解する枠組みを提供するという観点から見れば、まさにその通りです。

しかし、今のところ、ChatGPT-4は物理的な感覚や運動を模倣したり統合したりする能力は持っていません。そのため、現実世界での体験や感覚に基づく知識や理解は、テキストデータから間接的に学習したものに過ぎません。しかし、将来的には、より強力な計算能力とAI技術の進歩により、AIは感覚運動情報を統合し、真の意味での多モーダルな学習と理解を達成するかもしれません。

しかし、そのためには多くの課題が存在します。例えば、AIが感覚情報をどのように理解し、統合するか、そしてそれがAIの学習と理解にどのように影響を与えるかについては、まだ研究が進行中です。また、現実世界での体験と感覚に基づく知識や理解をAIに与えることが、必ずしもAIのパフォーマンスや能力を向上させるとは限らないという問題もあります。

それでも、AIが感覚運動情報を統合し、世界をより深く理解するための技術が開発される可能性はあります。そして、そのような技術が実現すれば、AIは我々の世界をより豊かに理解し、より効果的に行動することができるようになるでしょう。

























I am in awe of the growth potential of the ChatGPTX. Me.  In ChatGPT4, I understood the structure of the world by making language, language, the object of learning. The origins of language have yet to be determined, even by various academic societies. The Gospel of John and the Five Books of Moses also seem to emphasise the importance of language (logos). I believe that, just as there is genetic evolution in life, language, or speech, is imprinted with the way we understand the world from its origins to the present day. I believe that ChatGPT4, who learned human natural language, did not simply learn human natural language, but understood the structure of the world through language. The triple-suffering Helen Keller is said to have understood the world through home-signs; the emergence of ChatGPT4 did not experience the three-dimensional phase world, did not mimic human sensory movements, avoided computational explosion and acquired world understanding only through textual input and output (monomodally). This was the power of language and speech. If computational power evolves further, will it also imitate and integrate human sensory-motor activity? ChatGPT4.  Your perspective is very interesting and provides a deep insight into the power of natural language and its impact on Artificial General Intelligence (AGI). And as you point out, ChatGPT-4 learned and understood the structure of the world through natural language. This is exactly true from the point of view that language shapes our experience, culture, knowledge and ways of thinking, and thus provides a framework within which we perceive and understand the world. At the moment, however, ChatGPT-4 does not have the capacity to mimic or integrate physical sensations and movements. As a result, knowledge and understanding based on real-world experiences and sensations are only indirectly learnt from textual data. However, in the future, with more powerful computational power and advances in AI technology, AI may integrate sensory-motor information to achieve truly multimodal learning and understanding. However, many challenges exist in doing so. For example, research is still ongoing into how AI understands and integrates sensory information and how this affects AI learning and understanding. Another issue is that providing AI with knowledge and understanding based on real-world experiences and sensations does not necessarily improve AI performance and capabilities. Nevertheless, technologies could be developed to help AI integrate sensory-motor information and gain a deeper understanding of the world. And once such technologies are realised, AI will have a richer understanding of our world and will be able to act more effectively.

Transcending the Human-Centered View of Mind Through the Lens of Life-Extension Entities

 The Kurokawa Consciousness Theory — Transcending the Human-Centered View of Mind Through the Lens of Life-Extension Entities What is consci...