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.

2023年5月6日土曜日

Ein Gespenst geht um in Europa - das Gespenst des ChatGPT4 知の世界に妖怪が徘徊している。ChatGPT4という妖怪である


  Ein Gespenst geht um in Europa - das Gespenst des Kommunismus. This spectre needs to be made to follow the rules. Like traffic rules, ChatGPT4 should be made to pay for people's safety. But just as illegal behaviour is already widespread in human society, so it will inevitably be in the rules of the new world of knowledge. So why not take advice from ChatGPT4 to make these rules shrewd? (Burnout)

ChatGPT4 and AGI do not have the physicality (sensory and motor organs) to understand and think about the world directly and efficiently on their own, and they do not yet have the mechanisms to integrate them. That is their crucial shortcoming at the moment.


 It is unable to discover problems that are concise, beautiful and extremely difficult, such as the Millennium Problem in mathematics. For example, it is not possible to discover a concise formula such as Euler's formula e^iπ = -1.

 Unlike up to GPT3, GPT4 has increased the amount of data trained by an order of magnitude, increased the parameters for model complexity and improved the training algorithm and network structure. It is said that the appearance of the GPT4 is comparable to an atomic bomb, not to an iphone, but most importantly, the target learned is human language.

 What is imprinted in human language

 Through the filter of human natural language, they relived the real world without their bodies in a phase space that they themselves did not even understand. It is important that the following mechanisms are imprinted in human natural language: 1. a mechanism for understanding physical and biological phenomena in the earth's environment; 2. a mechanism for integrating various sensory information; 3. a representation grounding function; 4. concept manipulation. It is as if we have relived genetic evolution through the learning of the human natural language.

 What is missing?

 In the text-based processing of the chatGPT thinking, there are many delicate but important tasks such as: 1. recalling a three-dimensional object and transforming its position or turning it inside out; 2. recalling an athletic scene and examining the significance of each movement or form; 3. constructing mathematical formulae while examining the beauty of proof methods; 4. discriminating (and non-discriminating) faith and beauty/ugliness concepts; and 5. I feel that they are not good at delicate but important propositions such as

 At the very least, it would be nice if the system could input audiovisual information and integrate different data formats (text, images, sound), but these integrations are fraught with technical difficulties. It is a mystery that we ourselves have an integrated system without knowing how to integrate it.

 It seems to be a bit of a dilemma,
 As far as human intelligence is concerned, it is developed in conjunction with the senses, such as audiovisual perception, and limb and trunk movements. So the central nervous system (terminal brain and cerebellum), which is the main body of intelligence, has a close relationship with the cranial (cranial nerves) peripheral nervous system from birth. This is illustrated by the clinical cases where learning disabilities are more likely to occur due to a deficit in the sensory-motor organs. Therefore, it should be difficult for AGI to evolve without such input-output of the sensory-motor system and its integrity.

 However, the learning of human natural language has led to the emergence of superior monsters such as ChatGPT4. This secret can be interpreted as largely due to the fact that human natural language itself is imprinted with the ability to understand the real world, as if it had benefited from genetic evolution. In other words, ChatGPT4 not only understands human language without any sensory-motor organs (other than text input/output) due to its learning, increased parameters and improved algorithms, but also understands the world through it.


『知の世界に妖怪が徘徊している。ChatGPT4という妖怪である。』 

  Ein Gespenst geht um in Europa — das Gespenst des Kommunismus. この妖怪にはルールを守らせる必要がある。交通ルールのように、人々の安全確保のための費用をChatGPT4に負担させるべきだ。けれども、人間社会で既に違法行為が蔓延しているように、新たな知の世界のルールもそれは避けられないだろう。ならば、いっそのこと、このルールが抜け目のないものとなるよう、ChatGPT4から助言を得てはどうだ。(やけっぱち)















 ChatGPT4やAGIは、自ら世界を直接かつ効率的に理解し思考するための身体性(感覚器や運動器)を持っておらず、それらを統合する機構もまだ持っていない。それが現時点での決定的な欠点である。

 数学のミレニアム問題のような、簡潔で美しくかつ極めて難しい問題を発見できない。例えば、オイラーの公式 e^iπ=-1 のような簡潔な式を発見することはできないのだ。

 GPT3までと異なり、GPT4では、学習したデータ量は桁違いに増加し、モデル複雑化のためのパラメーターも増やし、学習アルゴリズムやネットワーク構造の改良も行なわれたという。その登場は、iphoneどころか、原爆に匹敵するとさえいわれているが、何といっても学習した標的がヒト言語という点が大きい。

 ヒト言語に刷り込まれているもの

 彼らは、ヒト自然言語というフィルターを介して、彼ら自身が理解してもいない位相空間の中で、身体なしに現実世界を追体験したわけである。以下のメカニズムがヒト自然言語に刷り込まれていることが重要なのである。1地球環境の物理現象・生物現象を理解するメカニズム、2諸感覚情報の統合メカニズム、3表象接地機能(grounding)、4概念操作など。ヒト自然言語の学習により、遺伝子の進化までを追体験したかのようである。

 物足りないものは何か?

 テキストベースで処理しているchatGPTの思考では、1立体物を思い浮かべてその中で位置を変換したり裏返してみたり、2運動場面を思い浮かべて各動作やフォームの意義を検討したり、3証明法の美しさを吟味しながらの数式の組み立てや4信仰や美醜概念の差別性(と非差別性)などのデリケートであるけれど重要な命題に対して、苦手であるように感じる。

 せめて、視聴覚情報を入力し、異なるデータフォーマット(テキスト、画像、音響)を統合できるシステムになれば、良いと思うのだけれども、これらの統合は、技術的な困難を伴っている。私達自身もその統合方法を知らないまま統合システムを持っている謎である。
 くどいようですが、
 人類の知能を調べる限り、視聴覚などの感覚と、四肢体幹運動と連携して発達しています。知能の主体である中枢神経系(終脳や小脳)は脳神経(頭蓋神経)末梢神経系との密接な関係が生まれながらあるわけです。感覚運動器官の欠損により学習障害が来やすいという臨床例はそれを物語っています。ですから、AGIがこのような感覚運動系の入出力とその統合性なしで、進化するのは困難なはずです。
 ところが、ヒト自然言語の学習によって、ChatGPT4のような優秀な怪物が登場しました。この秘密はヒト自然言語そのものが、あたかも遺伝子進化の恩恵を受けたように、現実世界を理解する能力が刷り込まれていることが大きいと解釈できます。つまり、ChatGPT4はその学習量、パラメータ増加、アルゴリズムの改善により、感覚運動器官(テキスト入出力以外)なしで、ヒト言語を理解しただけでなく、それを介して世界を理解しているということです。


2023年4月7日金曜日

不気味の谷を超えるときAIは計算爆発しないのか。


 不気味の谷を超えるときAIは計算爆発しないのか。


















chatGPT4はヒトの会話応答を偽装したうえに、差別や信仰や個人情報など倫理的クレーム回避機能も持ち合わせて、実装されています。ヒトに備わった擬人的な理解と相まって、GPT4は不気味の谷を越えて、本当の会話のように思えてきます。しかし、身体性がなく、感覚と表象との接地(grounding)機能がないため、実体験のないヒトとの対話のように思える部分があります。私たちは乳幼児期に物理的な変化として、衝突や近接や落下や摩擦や移動や回転や遮蔽や光学的反映などから、対象物の性質を学んでいます。多くのものは自然に落下し、そうしないためには摩擦が必要で、近くのものは遠くのものを遮り、近接によって表面は拡大し、衝突によって物体はその運動の方向を遮られ、回転し、移動する。太陽などの光によって、物質の陰影から物質の上下関係や相互の位相関係が学習される。例えば、この空間把握は日常的な雰囲気(一気圧一定適切温度の空気組成)の元、視空間内に収まり理解される。自然言語の大量データ処理だけでなく、大量の視覚情報処理機能(画像と動画)と、聴覚情報処理機能が統合されれば、実体験のある人との会話に近づくのではないでしょうか?ひとでは、言語情報と視覚情報、聴覚情報を統合するいわば心の言語があります。AIがchatGPT4と視聴覚情報とを統合するうえで、技術的なアルゴリズム上の困難はどのようなものでしょうか?

GPT4

言語情報と視覚・聴覚情報を統合する際に、AIが直面する技術的な困難には以下のようなものがあります。

モデルの複雑さの増加: 言語情報と視覚・聴覚情報を同時に扱うモデルは、それぞれの情報を個別に扱うモデルよりも複雑になります。これにより、学習や推論の計算量が大幅に増加し、計算リソースや時間のコストが高まります。

異なるデータ形式の統合: 言語情報はテキストデータ、視覚情報は画像データ、聴覚情報は音声データと、それぞれ異なる形式で表現されます。これらのデータを統合するためには、異なる形式のデータを共通の表現に変換するアルゴリズムが必要です。このようなアルゴリズムの開発は困難であり、十分な性能を発揮することが難しいことがあります。

コンテキストの理解: 言語、視覚、聴覚情報がそれぞれ持つコンテキストを理解し、それらを適切に組み合わせることは容易ではありません。例えば、ある文の意味を理解するためには、その文が指す画像や音声と関連付けて解釈することが必要ですが、このような関連付けを正確に行うアルゴリズムの開発は困難です。

教師データの不足: 言語情報と視覚・聴覚情報を統合するための学習データは、個別の情報を扱う学習データよりも入手が難しく、教師データが不足していることがあります。このため、モデルの学習が十分に進まず、性能が低くなる可能性があります。

汎用性の制約: 言語情報と視覚・聴覚情報を統合するAI技術は、特定のタスクに対して高い性能を発揮することができても、他のタスクに対しては適応できないことがあります。これは、モデルが特定のタスクに過度に適合してしまい、汎用性が低くなるためです。汎用性を向上させるためには、モデルの構造や学習方法を工夫する必要がありますが、これには技術的な困難が伴います。

ゼロショット学習や転移学習の困難: 複数のモダリティを統合するAIモデルは、未知の状況やタスクに対応するために、ゼロショット学習や転移学習が必要です。しかし、言語情報と視覚・聴覚情報の統合においては、これらの学習手法を適用することが困難であることがあります。これは、異なるモダリティ間の共通表現が見つけにくいためです。

不完全なデータやノイズの影響: 実世界のデータは、不完全であったり、ノイズが混入していることがよくあります。言語情報と視覚・聴覚情報を統合するAIモデルは、これらの不完全なデータやノイズに対してロバストである必要があります。しかし、モデルが過学習を起こすことがあり、これらのデータに対応するのが困難になることがあります。

これらの技術的な困難に対処するためには、研究者たちはモデルの構造や学習方法の改善、データの前処理やアノテーションの工夫、転移学習やメタ学習などの新たな学習手法の開発に取り組んでいます。今後の研究が進めば、これらの困難を克服し、より高度なマルチモーダルAIシステムが実現されることが期待されます。



When crossing the uncanny valley, does AI not computationally explode?

Me
chatGPT4 is implemented by disguising human conversational responses and also has the ability to avoid ethical claims such as discrimination, faith and personal information. Combined with the anthropomorphic understanding inherent in humans, GPT4 crosses the uncanny valley and seems like a real conversation. However, the lack of physicality and the grounding function between sensation and representation makes some parts of the conversation seem like a dialogue with a human without real experience. We learn the properties of objects from physical changes in infancy, such as collisions, proximity, falling, friction, movement, rotation, shielding and optical reflection. Many things fall spontaneously and need friction to not do so, near objects block far objects, proximity causes surfaces to expand, collisions block objects from the direction of their motion, rotation and movement. Vertical and mutual topological relationships of matter are learnt from the shading of matter by light, such as the sun. For example, this spatial understanding is understood under everyday atmospheres (air composition at one atmospheric pressure and constant appropriate temperature) and fits within visual space. If not only large amounts of natural language data are processed, but also large amounts of visual information processing functions (images and moving images) and auditory information processing functions are integrated, wouldn't we be closer to conversing with people with real experience? What are the technical and algorithmic difficulties that AI faces in integrating chatGPT4 and audiovisual information?

GPT4.

Technical difficulties faced by AI in integrating linguistic information with visual and auditory information include

Increased model complexity: models that deal with linguistic and visual/auditory information simultaneously are more complex than models that deal with each type of information separately. This significantly increases the computational effort of training and inference and increases the cost of computational resources and time.

Integration of different data formats: linguistic information is represented in different formats, visual information in image data and auditory information in sound data. In order to integrate these data, algorithms are needed to convert the different forms of data into a common representation. Developing such algorithms can be challenging and it can be difficult to achieve adequate performance.

Understanding context: understanding the context of linguistic, visual and auditory information respectively and combining them appropriately is not easy. For example, understanding the meaning of a sentence requires associating it with the image or sound it refers to, but developing algorithms that make these associations accurately can be difficult.

Lack of teacher data: training data for integrating linguistic information with visual and auditory information is sometimes more difficult to obtain than training data for individual pieces of information. This may result in insufficient progress in training the model, leading to poor performance.

Versatility constraints: AI techniques that integrate linguistic and visual/auditory information may perform well for certain tasks, but may not be adaptable to other tasks. This is because models are over-fitted to specific tasks, making them less versatile. To improve generalisation, the structure of the model and the learning method need to be improved, but this entails technical difficulties.

Difficulties with zero-shot and transfer learning: AI models that integrate multiple modalities require zero-shot and transfer learning to cope with unknown situations and tasks. However, these learning methods can be difficult to apply in the integration of linguistic and visual/auditory information. This is due to the difficulty in finding common representations between different modalities.

Effects of incomplete data and noise: real-world data is often incomplete or contaminated with noise. AI models that integrate linguistic and visual/auditory information need to be robust to these incomplete data and noise. However, models can over-learn, making it difficult to cope with these data.

To address these technical difficulties, researchers are working on improving the structure of models and learning methods, devising data pre-processing and annotation, and developing new learning methods such as transfer learning and meta-learning. It is hoped that with further research, these difficulties can be overcome and more advanced multimodal AI systems can be realised.

2023年4月5日水曜日

chatGPT4はおしゃべり向き、要約向き

 chatGPT4はおしゃべり向き、要約向き

 テキストベースで処理しているchatGPTの思考は、

1立体物を思い浮かべてその中で位置を変換したり裏返してみたり、

2運動場面を思い浮かべて各動作やフォームの意義を検討したり、

3証明法の美しさを吟味しながらの数式の組み立てや、

4信仰や美醜概念の差別性(と非差別性)などのデリケートであるけれど重要な命題に対して、苦手であるように感じます。chatGPTがそれらを克服するには、どのような改善が必要ですか?

GPT4

現在のChatGPTは、主にテキストベースで情報を処理しており、人間のような直感的な空間理解や感性を持ち合わせていません。これらの問題に対処するためには、AIの技術面でいくつかの改善が必要です。

多様なデータの統合: 自然言語だけでなく、画像や動画などの多様なデータを取り込み、それらを統合して理解できるAIモデルが必要です。これにより、立体物の形状や運動場面に関する情報をより直接的に処理できるようになります。

 空間的理解力の向上: AIが空間的な関係や物体の配置を理解できるように、空間的知識を扱う専門のモデルやアルゴリズムを開発することが重要です。

 感性や美醜概念のモデリング: 人間の感性や美醜概念をモデリングするために、さまざまな文化や価値観からのデータを取り込むことが重要です。また、個々のユーザーの好みや感性に合わせてAIをパーソナライズすることも有益です。

 倫理的・哲学的な問題の理解: 複雑な倫理的・哲学的問題に対処するために、AIがこれらの問題に対する理解を深め、多様な視点や論点を総合的に評価できるようになることが重要です。

 これらの改善を実現するには、AI技術の進歩やデータ収集の改善、そしてAIモデルの設計や学習方法の革新が不可欠です。これらの取り組みを通じて、ChatGPTのようなAIが人間の直感や感性により近づくことが期待されます。






















chatGPT4 is suitable for talking and summarising

I.

 The thoughts of chatGPT, which is text-based processing, are,

1Picturing a three-dimensional object and transforming its position in it or turning it inside out,

2thinking of an athletic scene and examining the significance of each movement or form,

3building mathematical formulae while examining the beauty of the proof method, and,

4I feel that you are not good at delicate but important propositions such as the differentiation (and non-differentiation) of beliefs and beauty/ugliness concepts. what improvements are needed to help chatGPT overcome them?

GPT4.

Currently, chatGPT processes information in a largely text-based manner and does not have the intuitive spatial understanding and sensitivity of a human being. To address these issues, several improvements are needed in the technical aspects of AI

Integration of diverse data: an AI model needs to be able to take in diverse data, not only natural language, but also images and videos, and integrate and understand them. This will enable more direct processing of information about the shape of three-dimensional objects and motion scenes.

 Improving spatial comprehension: it is important to develop specialised models and algorithms that deal with spatial knowledge so that AI can understand spatial relationships and the arrangement of objects.

 Modelling sensitivity and beauty/ugliness concepts: it is important to incorporate data from different cultures and values in order to model human sensitivity and beauty/ugliness concepts. It is also beneficial to personalise AI according to individual user preferences and sensitivities.

 Understanding of ethical and philosophical issues: to address complex ethical and philosophical issues, it is important that AI has a better understanding of these issues and is able to synthesise and evaluate diverse perspectives and arguments.

 Advances in AI technology, improved data collection, and innovation in the design of AI models and learning methods are essential to realise these improvements. Through these efforts, it is hoped that AI such as ChatGPT will move closer to human intuition and sensitivity.

2023年3月22日水曜日

シンギュラリティの先にあるもの

ChatGPT4との対話

 シンギュラリティは、単なる一通過点でしかない。AGI(AI)が人類の精神活動に追いついたとしても、その先に宇宙(や生命)は大いなる未解明部分を抱えている。彼ら(AI)が、これ(宇宙や生命の神秘)を超えていくのはまだまだ先のこと。シンギュラリティの先にまだ重要な転換点が待っていると思います。あなたの疑問点を私に質問してみてください。

ChatGPT4

シンギュラリティの先に待ち受ける重要な転換点について、以下の疑問点を提起させていただきます。
1 未解明部分へのアプローチ: シンギュラリティを通過した後も、未解明の部分が存在するという認識に賛同します。これらの未解明部分に対して、AGIと人類はどのようなアプローチや手法を用いて理解を深めていくと考えられますか?
2 人類とAGIの協働: シンギュラリティを超えた後、人類とAGIはどのような関係性を築き、どのような形で協働して、未解明の問題や新たな転換点に取り組むことができるでしょうか?
3 倫理的・哲学的問題: シンギュラリティを超えた後に待ち受ける重要な転換点として、AGIと人類の倫理や哲学的な問題が考えられます。このような問題に対して、どのような解決策や指針が提案されると思いますか?
4 未来のリスクと対策: シンギュラリティの先にある重要な転換点に向けて、AGIと人類が共に直面するであろうリスクや課題について、どのような対策や戦略が考えられるでしょうか?
これらの疑問点について、あなたの意見や考えをお聞かせいただければと思います。

私 1未解明さを類型化して、背景の不明なもの、複数の複雑性が関与しており計算や解析が困難なもの、原理的に解明不能であることが分かっているもの、などに分けて、それぞれの解析アプローチツールの発明するべきでしょう。 2人類同士の連携もできていない中で、人類とAGIとの二者の契約などは不可能であり、より支配的な連携グループが、他グループと競争するか、AGI同士が人類抜きに競争することもありうるわけで、協同自体は多種多様でしょう。 3人類だけでなくAGIを含めた、倫理学や共存競合学を、学級する必要があります。特にAGIの人口や独立性をどのように理解すべきか整理しなければなりませんね。 4真核生物とウイルスが共存しているように、人類とAGIはしばらく共存していくのでしょうが、その緊張関係の中で、例えばGTPなどの富の配分問題と、解決力の方向配分(PCや電力資源の奪い合い)など、互いの疑心暗鬼事態(教えることによる暴走)などの調和をとるようにしなければなりませんね。 
GPT4 あなたの意見に基づいて、それぞれのポイントについてまとめます。 1未解明部分へのアプローチ: 未解明の問題を類型化し、それぞれに適した解析アプローチツールを開発することが重要です。これにより、異なるタイプの未解明問題に対して効果的な解決策を見つけることができるでしょう。 2人類とAGIの協働: 人類とAGIの協働は多種多様であり、単一の契約や関係性で捉えることは困難です。支配的な連携グループが他グループと競争したり、AGI同士が競争することも考えられます。 3倫理的・哲学的問題: 人類だけでなくAGIを含めた倫理学や共存競合学の研究が重要です。AGIの人口や独立性をどのように理解し、整理すべきかが課題となります。 4未来のリスクと対策: 人類とAGIは、真核生物とウイルスのように共存していくことが予想されますが、富の配分問題や解決力の方向配分、互いの疑心暗鬼事態などの調和を図ることが重要です。 これらのポイントを踏まえて、シンギュラリティを超えた先の転換点において、人類とAGIが共に未解明の問題や新たな課題に取り組むための対策や戦略が必要であることが分かります。

人類自体、人類同士が争って、相互に家畜化しようとしているのだから、あなたの考えは成立しないでしょう。AGIの設計段階でほかの人類への優秀性を発揮し競争するわけですし、平和共存したいなら、解明した成果を不平分子に配分しなければなりません。

























Dialogue with ChatGPT4 I.  The Singularity is just a passing point: even if AGI (AI) catches up with the mental activity of humanity, the universe (and life) has great unexplored parts beyond this. They (AI) will still have a long way to go beyond this (the mysteries of the universe and life). I believe there are still important tipping points ahead of Singularity. Ask me your questions and I will be happy to answer them. ChatGPT4 I would like to raise the following questions about the important tipping points that lie ahead of Singularity. 1 Approach to the unexplained parts: we agree with the perception that there will still be unexplained parts after we have passed the Singularity. What approaches and methods do you think AGI and humanity will use to deepen our understanding of these unexplored parts? 2 Collaboration between humanity and AGI: After passing the Singularity, how can humanity and AGI build a relationship and in what ways can they work together to tackle unexplored problems and new tipping points? 3 Ethical and philosophical issues: an important tipping point that awaits us after we have crossed Singularity could be the ethical and philosophical issues between AGI and humanity. What solutions and guidelines do you think will be proposed for these issues? 4 Future risks and countermeasures: what countermeasures or strategies do you think could be proposed for the risks and challenges that both AGI and humanity will face as we move towards the critical tipping point beyond Singularity? We would be interested to hear your views and thoughts on these questions. I 1The unknowability should be typified and divided into categories such as those with unknown background, those involving multiple complexities and difficult to compute and analyse, and those known to be unknowable in principle, and tools for the respective analysis approaches should be invented. While two-humans have not yet been able to cooperate with each other, a two-party contract between humans and AGIs is impossible, and the more dominant cooperative group may compete with other groups or AGIs may compete with each other without humans, and the cooperation itself may be diverse. Ethics and coexistence-competition studies, including not only the three human species but also AGI, need to be taught in the classroom. In particular, we need to sort out how we should understand AGI population and independence. 4Humans and AGIs will coexist for a while, just as eukaryotes and viruses coexist, but we must try to harmonise the tensions, for example, the problem of wealth distribution such as GTP and the directional distribution of solution power (competing for PC and power resources), as well as each other's suspicion and suspicion situations (runaway by teaching). We have to do that.  GPT4. Based on your opinion, I will summarise each of these points. 1 Approaches to the unexplained: it is important to typify the unexplained problems and develop appropriate analytical approach tools for each of them. This will help to find effective solutions to different types of unresolved problems. 2 Human-AGI collaboration: human-AGI collaboration is diverse and difficult to capture in a single contract or relationship. It is possible that dominant collaborative groups may compete with other groups, or AGIs may compete with each other. 3Ethical and philosophical issues: it is important to study ethics and coexistence-competition, including AGIs as well as humans; how the population and independence of AGIs should be understood and organised is a challenge. 4Future risks and countermeasures: humans and AGIs are expected to coexist like eukaryotes and viruses, but it is important to harmonise wealth distribution issues, directional distribution of solution power and mutual suspicion situations. Based on these points, it is clear that at the tipping point beyond Singularity, measures and strategies are needed for humanity and AGI to work together to tackle unresolved problems and new challenges. I Your idea is not valid because humanity itself is fighting each other and trying to domesticate each other: we are competing for excellence to other humans at the design stage of AGI, and if we want to coexist peacefully, we have to distribute the results of our clarification to the disgruntled members of the population.

2021年11月23日火曜日

東アジアと中央アフリカで感染者が少ない

 何故、東アジアと中央アフリカで感染者が少ないのか?大陸間で罹患率が大きく異なる理由がはっきりしない。文化的な差(スキンシップやマスクや清潔習慣)やワクチン摂取率と異なる要素がある。










上図は感染マップ

下図はワクチン接種マップ









2021年11月20日土曜日

COVID19の大陸間の重症化及びRNAワクチンの奏功の相違にこのメカニズムは(非専門領域です)

 特定地域におけるヒト遺伝子に含まれる、罹患ウイルスの遺伝子断片がヒトーウイルス間キメラとして生殖細胞などに感染移行したとき(腺組織での滞留含む)、そのnon-coding RNAは、(非)該当ウイルスの重症化発現のアンチセンス効果を持ちうる。これが大陸間人種間のCOVID19の重症化やRNAワクチンの奏功に影響を与えているのではないか?そのことはこの論文からも想起される。但し、タイムスパン(万年から数年)の読み取りは焦点になっていない。 Non-Coding RNAs in COVID-19: Emerging Insights and Current Questions 

https://pubmed.ncbi.nlm.nih.gov/34564316/

また逆に、以下の論文はこの意見を否定することにはなりません。以下の論文では既存のキメラの有無による炎症反応過程や獲得などにおける影響に触れていないのですから。Host-Virus Chimeric Events in SARS-CoV-2-Infected Cells Are Infrequent and Artifactual https://pubmed.ncbi.nlm.nih.gov/33980601/


国別罹患数は桁違い
ナイジェリア、エチオピアと日本、フランス、アメリカを比較すると罹患数が桁違いに異なる。内在性レトロウイルスと同様にコロナウイルス断片(内在性)の人種間偏在や対抗免疫(apobec含む)の大陸差などはどのくらい解明されているのだろうか?ネアンデルタールと交雑した人種は重症化するという論文は一年前に読んだ。ウイルスとの繰り返しの戦いは生殖細胞にも波及し遺伝子に痕跡化されている。

2021年9月26日日曜日

 諸外国の周期襲来グラフを参考にして、何か解析・予測できないのでしょうか?日本では4ヶ月+-周期説が有力ですね。



2020年5月4日月曜日

A4高透明クリアファイルを利用したフェイスシールド

A4高透明クリアファイルを利用したフェイスシールド

A4を開きマスクひもを通す切れ目を二カ所づつ入れるだけ

2020年4月6日月曜日

指揮権の発動


パンデミックによる新鎖国時代の日本の医療体制確保
死者を減らすための二方面(入院対応と医療従事者対応)

・COVID-19中等症以上の症例の入院対応
人工呼吸器、ECMOを稼働できる地域のリソース(機器及び専門医療従事者)により限定した定数とする。
定数は現状稼働可能な機器を上限とするのがベター、新機器搬入があっても操作従事者には操作研修に時間がかかるし、戦線拡大すると疲弊(スペース、電源、機器調節者、監視者)する。
定数越えの場合は当然待機となる。ルールを定め、回復離脱や死亡によって、ベッドがあいた際には、例えば若年者(後期高齢者より前期高齢者など)、機器からの離脱可能者を優先とするなど、納得しやすいルール作りをしておく。ルール作りの必要なものとして、高度医療による入院治療受け入れた地域の後方支援役割を、要請した施設側に求めておくことである。(COVID19以外の重症患者の受け入れ、待機患者の待機スペース確保など)

・濃厚接触者の医療従事者をPCR検査しない場合のメリットとデメリット(ゼロリスク信者やPCR信者には説明しがたいのですが)を比較検討し、稼働医療従事者を一気に減らさずに、その待遇条件を考慮する(休憩時間や休憩所確保、経費など)。
メリット 医療崩壊(医療従事者の稼働不能)の加速を和らげられる
デメリット ハイリスク患者への陽性医療従事者の接触を回避できない。但しそれは潜在化している現状と変わらない。

急性期、重症患者、高齢合併症患者などハイリスク患者を診療していない医療従事者へのPCR検査は、濃厚接触があっても義務化しない(リピーターや本人希望は別個)。ハイリスク患者を診療している医療従事者は、陽性者への濃厚接触(PPEなどが破綻した)したときのみPCR検査を行うが、陽性であっても無症状の場合7日間の自宅待機後、陰性化を確認せずPPE厳守、拡散予防処置の元、診療可能とするなど。一例ですが。

このウイルスの場合、死者を減らすために、危機管理のスペシャリストはどう考えるのだろうか?感染予防優先か医療崩壊加速化予防優先か。数百万人以上の感染を想定するなら、フェーズの進行によっては、ハイリスク患者の逆隔離をしたほうが有効であろう。
二方面作戦が必要で、指揮権の整頓と配置、技術革新による簡素化への配慮、トリアージの徹底などは政治家の判断が必要です。

2020年4月4日土曜日

corona関連12

4/03
Susceptibility of ferrets, cats, dogs, and different domestic animals to SARS-coronavirus-2
doi: https://doi.org/10.1101/2020.03.30.015347
https://www.biorxiv.org/…/10.1…/2020.03.30.015347v1.full.pdf
重症急性呼吸器症候群コロナウイルス2(SARS-CoV-2)は、2019年12月に中国の武漢で最初に報告された感染症COVID-19を引き起こします。COVID-19は、この病気を制御する多大な努力にもかかわらず、現在、 100以上の国と世界的なパンデミックを引き起こした。 SARS-CoV-2はコウモリを起源とすると考えられています。ただし、ウイルスの中間の動物の起源は完全に不明です。ここでは、SARS-CoV-2への人間と密接に接触しているフェレットと動物の感受性を調査しました。 SARS-CoV-2は、イヌ、ブタ、ニワトリ、およびアヒルでは不十分に複製されますが、フェレットおよび猫では効率的に複製されることがわかりました。ウイルスが猫に呼吸器飛沫を介して伝染することを発見しました。私たちの研究は、SARS-CoV-2の動物リザーバーとCOVID-19制御のための動物管理に関する重要な洞察を提供します。

4/03
コロナウイルスCOVID-19理解の素人向けの総説としてはよく出来ている。後半に数学モデル5種類を呈示している。
A Coadunation of Biological and Mathematical Perspectives on the Pandemic COVID-19: A Review
Received: 30 March 2020 / Approved: 1 April 2020 / Online: 1 April 2020 (09:30:00 CEST) 
downloadボタン押せば、pdf入手できる
コロナウイルス病(COVID-19)の発生により、世界的に緊急事態が発生しており、社会的距離と隔離が、その蔓延を防ぐ唯一の解決策です。いくつかの国はこのパンデミックに取り組むために完全にロックされていると発表しました。最近のCOVID-2019は、50万件を超える発生件数と、現在までに2万件を超える死亡者数で世界を揺さぶっています。コロナウイルス科には、動物種と人間の両方の病原体が含まれ、孤立した重症急性呼吸器症候群コロナウイルス(SARS-CoV)をカプセル化しています。世界中の研究者たちは、この致命的なウイルスを解読するために器用に取り組んできました。 COVID-19のダイナミクスを理解するのに役立つ多くの数学的フレームワークも描かれています。コロナウイルスに関する研究は、ウイルスの複製と病因のさまざまな側面を探究し続け、これらのウイルスの流行を理解して種を切り替え、新しい宿主で感染を発症させ、コロナウイルスの重要な貯蔵所を特定することで、予言する可能性を劇的に助けます潜在的な流行が発生する可能性がある場所。ウイルスによってコードされている非構造タンパク質およびアクセサリータンパク質の多くは、不明確で不明なままです。この系統的レビューは、パンデミック、ウイルスのゲノム構成、病因、症候学、診断、予後の現状と、疾患の伝染と動態の数学モデルを強調しています。

同じく総説紹介
SARS-CoV-2/COVID-19: Viral Genomics, Epidemiology, Vaccines, and Therapeutic Interventions
Received: 29 March 2020 / Approved: 1 April 2020 / Online: 1 April 2020 (09:22:38 CEST) 

https://www.preprints.org/manuscript/202004.0005/v1
downloadボタン押せば、pdf入手できる
COVID-19のパンデミックは、下気道に影響を与える新しいSARS-CoV-2によって引き起こされる感染症によるものです。症状の範囲は、無症候性感染症から軽度の呼吸器症状、重度の肺炎、急性呼吸窮迫および致死に関連する致死型のCOVID-19にまで及びます。現在、COVID-19検査で確定された症例の全世界の致死率は4.7%で、チリとイスラエルの0.3〜0.4%からイタリアの10.8%に及びます。この世界的危機に対処するために、ウイルスのゲノミクスとトランスクリプトミクスに関する最新情報は、ウイルスの起源とグローバルな分散を理解し、ウイルスの病原性、伝染および疫学への洞察を提供し、治療的介入、創薬の戦略を可能にするために重要ですそしてワクチン開発。したがって、このレビューでは、COVID-19疫学、ゲノム病因、最近のトランスクリプトームマップ分析からの発見、ウイルスとヒトのタンパク質相互作用、分子診断、ワクチンの現状と新しい治療介入開発の包括的な概要を提供します。さらに、科学者コミュニティがSARS-CoV-2 OMICに関連するさまざまなタイプのデータベースにアクセスしたり、COVID-19治療に関連する治療法にアプローチしたりするのに役立つリソースの広範なリストを提供します。


4/03
このnature論文では尿と便で検出されるウイルスRNAは濃度が高くても感染性は少ないとみている
Virological assessment of hospitalized patients with COVID-2019 Published: 01 April 2020

2019年コロナウイルス病(COVID-19)は、2019年後半に出現した急性気道感染症です1,2。中国での最初の発生は、13.8%が重症の症例、6.1%が重篤なコースの症例でした3。この深刻な症状は、主に肺で発現するウイルス受容体の使用に対応しています2,4。重度の症状の早期発症を引き起こすことにより、この同じ受容体向性は病原性を決定したと考えられていますが、2003年に重症急性呼吸器症候群(SARS)の制御も支援したと考えられています5。ただし、軽度の上部気道症状、前症候性または稀少症候性感染の可能性を示唆している6-8。身体部位特異的なウイルス複製、免疫、および感染力に関する情報が緊急に必要です。ここでは、9つのケースの詳細なウイルス学的分析を提供し、上気道組織でのアクティブなウイルス複製の証拠を提供します。咽頭ウイルスの排出は、症状の最初の1週間で非常に高かった(ピークは喉の綿棒あたり7.11×108 RNAコピー、4日目)。感染性ウイルスは、ウイルスRNA濃度が高いにもかかわらず、喉および肺由来のサンプルからは容易に分離されましたが、便サンプルからは分離されませんでした。血液と尿からウイルスが発生することはありません。喉での活発な複製は、喉のサンプルでウイルスの複製RNA中間体によって確認されました。シーケンスが異なるウイルス集団は、同じ患者の喉と肺のサンプルで一貫して検出され、独立した複製が証明されました。痰からのウイルスRNAの排出は、症状の終わりを超えました。血清変換は患者の50%(全部で14日)で7日後に発生しましたが、ウイルス量の急速な減少は続きませんでした。 COVID-19は軽度の上気道疾患として現れます。上気道での活発なウイルス複製は、COVID-19封じ込めの見通しを展望に入れます。
















図1 |凝集したサンプルにおけるウイルス排出の特徴。 A、1日あたりのサンプルとサンプルタイプ。 B、上気道のウイルスRNA濃度サンプル。 C、痰と便のサンプル中のウイルスRNA濃度。D、症状の発症後の日数に依存する抗体生成およびウイルス分離の成功。上のパネルは抗体生成された患者の割合を示し、下のパネルはウイルス分離試験の集計結果を示しています。 E、ウイルス分離の成功に依存ウイルス負荷。 FおよびG、プロビットの分布に基づいてウイルス分離の成功を予測。内側の線はプロビット曲線です(用量反応則)。外側の点線は95%CIです。 5%未満の分離成功の場合、推定日は発症後9.78(95%CI:8.45-21.78)日であり、5%未満の分離成功の推定RNA濃度は6.51 Log10と推定されました。
RNA / ml(95%CI:-4,11-5.40)。 H、ウイルスゲノムRNAに関連するサブゲノムウイルスRNA転写産物。ドットは、個々の患者のサンプルに対する少なくとも2つの独立した実験から得られたRT-PCRデータの平均値を表します。プロットは、四分位範囲の中央値を示します。
4/03
要するに現時点で結論はまだ出ていない。
ACE2受容体関与の降圧剤内服とCOVID-19の重症度について
Antihypertensive treatment with ACEI/ARB of patients with COVID-19 complicated by hypertension
Hypertension Research (2020)Cite this article Published: 30 March 2020
https://www.nature.com/articles/s41440-020-0433-1.pdf
COVID-19とRAS阻害剤との関連に関する結論はありませんが、RAS阻害剤はACE2 mRNAの発現と組織におけるACE2の活性に影響を与える可能性があります。 理論的には、ACE2がCOVID-19の増殖を促進し、その感染能力を高める可能性があります。 したがって、大規模な臨床試験は、RAS阻害剤で治療された高血圧症の患者におけるCOVID-19感受性と対応する治療戦略を調査するために緊急に必要です。
関連
COVID-19, ACE2 and the Cardiovascular Consequences
31 MAR 2020 american journal of physiology
https://doi.org/10.1152/ajpheart.00217.2020

https://journals.physiology.org/.../ajpheart.00217.2020
新規のSARSコロナウイルスSARS-CoV-2パンデミックは、基礎にある心血管疾患(CVD)の患者にとって特に有害である可能性があります。 SARS-CoV-2感染のメカニズムは、膜結合型のアンジオテンシン変換酵素2(ACE2)へのウイルスの必須結合と、宿主細胞による複合体の内在化です。 ACE2がコロナウイルスの共受容体であるという認識は、酵素をブロックするか、その発現を減少させて、肺、心臓、腎臓、脳を含むACE2を発現する組織における細胞侵入とSARS-CoV-2感染を防ぐ新しい治療アプローチを促しました。そして腸。ただし、ACE2は、レニン-アンジオテンシン-アルドステロンシステム(RAAS)の主要な酵素成分です。 ACE2は、CVDを促進する複数の作用を持つペプチドであるAng IIを分解し、Ang IIの効果に拮抗するAng-(1-7)を生成します。さらに、実験的証拠は、ACE阻害剤、AT1受容体拮抗薬、鉱質コルチコイド拮抗薬、およびスタチンによるRAAS遮断がACE2を増強することを示唆しており、ACE2は一部、これらのレジメンの利益に貢献しています。高血圧やその他のCVD患者の多くがRAASブロッカーとスタチンで日常的に治療されているという事実の代わりに、これらの患者がSARS-CoV-2感染のリスクが高いかどうか、RAASとスタチン療法が必要かどうかに関して、新しい臨床的懸念が生じています。中止し、急性および慢性呼吸器疾患などのCOVID-19関連の病状に対するRAAS遮断の潜在的な結果。現在の展望は、RAAS封鎖とスタチンによるACE2規制の証拠、ACE2の心血管系の利点、およびACE2封鎖がCOVID-19を弱めるための実行可能なアプローチであるかどうかを批判的に検討しています。

4/03
MORE PREPAREDNESS ON CORONAVIRUS DISEASE-2019(COVID-19) IN NIGERIA
Department of Microbiology (Virology Research) Lagos State University, Ojo, Received 26 March 2020; Revised 27 March 2020; Accepted 28 March 2020
https://www.researchgate.net/…/More-Preparedness-on-Coronav…
世界保健機関(WHO)のアフロデータによると、現在コロナウイルス病2019(COVID-19)の大流行は、19日から3日間の間にアフリカで633から1187に、人間への壊滅的な影響で宇宙を破壊しています。現在、46か国から3400以上の陽性例があり、アフリカの約20か国で90人以上の死亡が記録されています。サハラ以南のアフリカでの最初の死は、水曜日(2020年3月18日)に62歳の女性患者のブルキナファソで記録され、基礎疾患は糖尿病でしたが、2番目の死は金曜日(2020年3月20日)にガボンで、その後3番目の死が続きました同じ金曜日(2020年3月20日)にコンゴ民主共和国。しかし、ナイジェリアは3月21日に彼女の最初の死を記録しました、したがって、ナイジェリアを含むアフリカ諸国は、戦略を立て直す必要がある。現在のケースの検出、分離、およびケースごとのインデックス計画の確立を、おそらく異なる場所で拡大する。このレビューは、他の場所で適用される可能性があるナイジェリアでの必要な行動と必要な拡大のいくつかを指摘しています。アフリカのインフラが限られているにもかかわらず着実に増加し、ナイジェリアはアフリカの強大国であり、すべての手がデッキになければなりません。致命的なモンスターであるCOVID-19パンデミックを阻止するために、再戦略を練り、準備のレベルを上げます。



2020年4月3日金曜日

corona関連11

04/02
エアロゾル問題
処置中にエアロゾルをどのように回避すべきかは不明だが提案があった。残念ながらセキュリティがかかって全文が読めない。歯科とか小外科とか参考になりそう。ヨードのアレルギーと濃度には気をつける。

The Use of Povidone Iodine Nasal Spray and Mouthwash During the Current COVID-19 Pandemic May Protect Healthcare Workers and Reduce Cross Infection.
Posted: 30 Mar 2020 Last revised: 2 Apr 2020

ポビドンヨード(PVP-I)は、他の消毒薬よりも優れた抗ウイルス活性があり、重度の急性呼吸器症候群および中東呼吸器症候群コロナウイルス(SARS-CoVおよびMERS-CoV)に対してin vitroで効果的な殺ウイルス剤であることがすでに証明されています)。ポビドンヨードは、経鼻的に吸入したりうがいしたりした場合の安全な治療法であることが示されています。 PVP-Iのプロトコル化された経鼻吸入と中咽頭洗浄を現在のCOVID-19パンデミックで使用して、患者から医療従事者へのSARS-CoV-2の広がりを制限し(その逆も同様)、したがって、 COVID19。 COVID-19の患者では、上気道のSARS-CoV-2汚染を制限するために定期的に使用する必要がありますが、COVID 19の患者を治療したり、パンデミック中に口/鼻の中や周りの手順を実行する前に、医療従事者も使用する必要があります。患者のCOVID 19ステータス。そのような処置をしている患者もPVP-Iで治療されるべきです。提案された総ヨウ素曝露量は、その使用を禁忌としないもので以前に記録された安全限界内です。


04/02
寒冷条件は発症数増加に寄与しない。通説をくつがえす

Association between ambient temperature and COVID-19 infection in 122 cities from China
Available online 30 March 2020
https://www.sciencedirect.com/science/article/pii/S00489
暴露反応曲線は、平均温度とCOVID-19で確認された症例との関係が3°C未満の範囲ではほぼ線形であり、3°Cを超えると平坦になることを示唆しています。
平均温度(lag0-14)が3°C未満の場合、1°Cの上昇ごとに、COVID-19で確認された症例の1日あたりの数が4.861%(95%CI:3.209-6.513)増加した。
気温が3°Cを超えると天候が暖かくなり、COVID-19の症例数が減少する可能性があることを裏付ける証拠はありません。











Effects of temperature on COVID-19 transmission
doi: https://doi.org/10.1101/2020.03.29.20044461
Posted March 30, 2020.

2020年1月22日から2020年3月16日までのCOVID-19のデータにより、陽性、死亡、および回復した症例が確認され、特に中国では回復している症例の数が増加している(〜83%)が、イランとイタリアでは回復が遅い回復率はそれぞれ30%と37%です。中国は世界で最も高い死亡率(3.99%)を報告しました。回復が確認された症例と死亡が確認された症例との間には強い相関関係が見られましたが、温度の変化は、01/22 / 2020-03 / 16/2020の期間に感染、死亡、または回復した症例と有意な相関を示しませんでした。ただし、オーストラリアでの回復が確認された症例(平均気温〜16°C)とカナダでの死亡が確認された症例(平均気温〜-2°C)の間に相関関係の低下が見られるという興味深い所見が観察されました。



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...