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.

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。

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...