  |
はてなキーワード: NATURALとは
Japan’s process of imperial expansion, however, put it on a collision course with the United States, particularly in relation to China.
To a certain extent, the conflict between the United States and Japan stemmed from their competing interests in Chinese markets and Asian natural resources.
岡崎体育、『なにやてってもあかんわ』、『まわせPDCAサイクル』『MUSIC VIDEO』『Natural Lips』
(でも、彼の歌でいちばん好きなのは『スペツナズ』『式』『龍』『チューリップ』やけどな
特にチューリップはくるりリスペクトがリップサービスじゃなかったんだってなった
声質的に『留学生』みたいなのがあっている気がするけど、天才だと思うから色んな曲出して欲しい
『knock out』の原作リスペクトのフワッと感も良かった)
あと、TSWの『埼玉 San Andreas』、ノリアキ『きみはポイズン』『Unstoppable』
外国の曲がよかったら、Kamini -『Marly-Gomont』
正確には曲じゃないしアーティストじゃないけど
『黒人が怒っている動画にビート流したらヒップホップになった』
Guo Wengui lied to hundreds of thousands of his online followers, promising them huge profits if they invested in GTV Media Group, Himalayan Farm Alliance, G| Club and Himalayan Exchange. Since at least March 2018, Guo Wengui has been the mastermind behind the complex financial scam, in which he and his financial adviser Kin Ming Je defrauded thousands of people and made more than $1 billion. Guo Wengui's success has a "cult" flavor. Calling believers in the name of "anti-communist", creating a community with closed information, while bullying or threatening to punish those who are not firm in their beliefs. After packaging himself as a "master" type of figure, it is natural to harvest the wealth of believers.
で、なんのグループを出していてどのようなprocessing（NLP＝Natural Language Processing）をどの段階でしているの？
Guo Wengui lied to hundreds of thousands of his online followers, promising them huge profits if they invested in GTV Media Group, Himalayan Farm Alliance, G| Club and Himalayan Exchange. Since at least March 2018, Guo Wengui has been the mastermind behind the complex financial scam, in which he and his financial adviser Kin Ming Je defrauded thousands of people and made more than $1 billion. Guo Wengui's success has a "cult" flavor. Calling believers in the name of "anti-communist", creating a community with closed information, while bullying or threatening to punish those who are not firm in their beliefs. After packaging himself as a "master" type of figure, it is natural to harvest the wealth of believers.
Why mass can distort spacetime?
https://physics.stackexchange.com/questions/230432/why-mass-can-distort-spacetime
So the energy and momentum flowed in, they may or may not be converted into mass by coupling together. But the curvature doesn't change unless the motion of the energy and momentum changes.
これで「エネルギー」と「モーメンタム」が流れ込めば「質量」が生まれることがわかる。しかしモーメンタムとエネルギーの運動に変化がなければ、曲率は変わらない。
では「質量とエネルギーは同じなのか」ということについてだが、測定単位がそろえば同じことだと説明がある。
https://physics.stackexchange.com/questions/554778/why-is-mass-a-form-of-energy
But particle physicists use natural units where they measure both mass and energy in electron volts. This would make sure that the difference of the sum of the masses of the resulting particles and the mass of the neutron is exactly the same as the kinetic energy of the resulting particles.
■ Regarding the free release of the new species previewed and the reason for making the support site the main platform for releasing new species:
While the free release on the Kurobinega website is at my discretion, I'm considering doing so roughly once every three or two paid releases.
The following might not be particularly relevant to English-speaking fans, or in other words, to everyone. The reason I'm focusing on early releases is that I want to limit the exposure of MGE and continue creating content on a smaller scale. First of all, I don't want MGE to be a hugely popular restaurant that anyone can enter, nor do I wish to become an internet celebrity. For me, MGE is akin to a reasonably popular local restaurant where like-minded individuals who share my interests gather. By scaling down, my production speed has increased. The period from Dragonewt to Tai Sui was shorter, and the next species should be released sooner. What matters most to me is creating the MGE I want to craft, drawing pictures, and developing games in the world of MGE. I'm delighted when people who value MGE's themes as I do get to see it. Receiving money on support sites like these, allowing me to spend more time on production, is truly appreciated.
Using the stuffed animal analogy again, it truly makes me happy when someone who genuinely loves and cherishes stuffed animals sees the ones I've created. Yet, I can't see those who say they adore stuffed animals but also tolerate and respect those who take pleasure in mutilating them as people who share the same love for stuffed animals as I do. I don't have the inclination to actively show them the stuffed animals I've made.
I believe English-speaking individuals, when witnessing a stuffed animal's head being torn off or the pleasure derived from it, would straightforwardly label it as "crazy." However, it's different in Japan, especially on social media. Even if they dislike watching the stuffed animals being hurt, they'll say, "Let's respect those who enjoy tearing them." This, despite seeing me, someone desperately protecting my stuffed animals, getting attacked by such individuals. There's a prevailing notion in the otaku community, especially on Japanese SNS (Social Media), that "All fetishes must be respected." Speaking out against this, even as a victim, can result in backlash. Not everyone thinks this way, but it's the dominant mindset. Disheartened by this, I didn't want to show them MGE anymore. When you grow to dislike a place, it's only natural to distance yourself, and that's what I've done.
However, this is a problem in Japan. In English-speaking regions, fans typically call out what they dislike, labeling it as "crazy." I have many English-speaking friends who've genuinely helped me in trying times. The MGEwiki admin is also a dear friend. Depending on the English-speaking fan community's dynamics, I might consider releasing content on MGEwiki a month after the early release.
I see that among men all things depend upon three wants and desires, of which the end is virtue, if they are rightly led by them, or the opposite if wrongly. Now these are eating and drinking, which begin at birth—every animal has a natural desire for them, and is violently excited, and rebels against him who says that he must not satisfy all his pleasures and appetites, and get rid of all the corresponding pains—and the third and greatest and sharpest want and desire breaks out last, and is the fire of sexual lust, which kindles in men every species of wantonness and madness.
私は、人間のあいだではすべてのことが三つの欲望に依拠していると見ています。それらは、正しく導かれれば徳であり、誤って導かれればその反対となります。まずは「食欲」と「飲欲」であり、これらは生まれたときから始まります。あらゆる動物が自然とその二つの欲望を備え、激しく興奮させられ、己の快楽や食欲を満たしてはいけないと言う者に逆らい、付随する苦痛からは逃れようとします。そして第三の、最も強く鋭い欲望が、最後に噴き出します。それは人々のあらゆる種類の淫気と狂気を燃え上がらせる「性欲」の炎です。
今のところこれが最古である。さすが西洋哲学の祖。「食」と「飲」が分かれているのが特徴。プラトンの著作は明治時代に翻訳されていて日本人にも知られていたと思われる。
欲界三欲
(一)飲食欲，即凡夫於種種美味之飲食，多生貪愛之心。(二)睡眠欲，即凡夫之心多暗塞，耽著於睡眠而不能勤修道業。(三)淫欲，即一切男女由互相之貪染，而起造諸種欲事。
欲界三欲
1. 飲食欲、すなわち凡夫はさまざまな美味の飲食において、多くは貪愛な心を生む。2. 睡眠欲、すなわち凡夫の心は暗く塞がり、惰眠に耽って修業に励むことができない。3. 淫欲、すなわちすべての男女は互いに貪欲に染まり、それがさまざまな欲事の原因となる。
『翻訳名義集』は中国・南宋時代に編纂された仏教系の書物。もちろん日本にも伝わっている。というかこの組み合わせが現在のスタンダードである。
いにしへの人三慾を忍ぶ事をいへり。三慾とは、飲食の欲、色の欲、睡の欲なり。
『養生訓』は江戸時代の大ベストセラー。貝原益軒は儒学者だが、この組み合わせは仏教の「三欲」と同じなので、「いにしへの人」というのは僧侶のことなのか。三欲を「抑えるべきもの」と捉えているのも仏教的である。「睡眠を減らすと健康になる」みたいなことも言っている。
『歌学提要』は幕末の歌人・香川景樹の理論をその弟子の内山真弓がまとめたものだという。
人間の根源の欲望を、食欲・性欲・表現欲に三大別して言うそのことは、江戸末期の巨匠香川景樹以来、歌界ではならいとなっている。
ということで「食欲」「性欲」「表現欲」を表しているらしい。
これはイギリス科学振興協会の当時の会長であったライアン・プレイフェアのスピーチが翻訳されたもののようだ。原文を当たると「かつての錬金術師は黄金・健康・不死のために賢者の石を研究していた」…みたいな内容だったらしい。
they hoped to attain the three sensuous conditions of human enjoyment -- gold, health, and immortality.
村上専精は僧侶だが仏教の「三欲」とは異なるのか。「生存欲」は戦時中の文章で「日本人は三大欲求の生存欲を抑えて国家に殉じるからすごい！」というふうに使われているのを見かけて面白かった。
人間の三大慾望たる衣食住
個人的に「衣食住」は欲望というより「基本的なもの」「必要なもの」というニュアンスで捉えていたのだが、井原西鶴の『世間胸算用』でも「分際相応に人間衣食住の三つの楽の外なし」と書かれているそうなので、あながち「欲望」的な捉え方でも間違いではないのか。似たようなパターンだと三大欲求を「福・禄・寿」に割り当てることもある。
美術評論家が三大欲求に「美欲」を入れるのは、歌人が「言語表現欲」を入れるのと似通っているか。
明治以降は経済発展もあってか「金銭欲（利欲・財欲）」や「名誉欲（出世欲）」を挙げることがかなり多い気がする。
もとはアメリカで1948年に刊行された小説だが、原文だと「three main pastimes」なので「三大娯楽」かな。
といった記述がある。
食欲、性欲、排泄欲の根源的意味に比べたら、人間の他の欲望である出世欲とか名誉欲とか権力欲とか支配欲とか金欲とか知識欲など、それこそ屁以下の価値しかない。
いわゆる「生理的欲求」のひとつとして食欲や睡眠欲と並べて語られる「排泄欲」だが、「三大欲求」として挙げられていることは少ない印象を受ける。ただ「性欲（射精欲）」を排泄欲の一種とみなすこともあるようだ。
本来、仲間と一緒にいたい、集団の中で自分の安定した位置を占めたいという欲求――集団欲は、食欲、性欲と並んで三大欲と言われる程のものである。
この「集団欲」を三大欲求とみなすのは戦後にかなり広まった感じがする。近年の書籍でも睡眠欲に代えて集団欲が挙がることがあるようだ。
貞潔・清貧・従順の修道三誓願は人間共通の三大欲求（肉欲・所有欲・支配欲）にかかわるものとして、生涯の一大試練と誘惑になりうる。
これはつまりカトリックの修道士が守る三誓願の対義語となるような欲望（貞潔↔肉欲 清貧↔所有欲 従順↔支配欲）を「三大欲求」と見なしているらしい。カトリックのあいだでポピュラーな解釈なのかは知らないが、三誓願そのものは3世紀末くらいまで遡るらしいので、当時からそうした発想があったとしたら面白い。
現在の一般的な認識。「金銭欲」「名誉欲」「集団欲」あたりを含めて「諸説あり」と言われていてもおかしくなかったと思うが、最終的にほとんど「食欲・睡眠欲・性欲」で固定されてしまったのは面白い現象である。
テーマ。
「リーゼントというのは前頭部の髪型（ポンパドール）ではなく後頭部の髪型（ダックテイル）のことだ」って本当なの？
だいたいの前回のまとめ。
さて、今回の記事の主眼は、前回の記事でも書いた「ポール・グラウス」という人物は何者か、というところにあるのだが、そのまえに増田英吉が戦前から「リーゼント」を施術していたという証拠を提示しておきたい。というのも国立国会図書館デジタルコレクションで検索したところ1936年の広告を見つけたのである。
スタア 4(21)(82) - 国立国会図書館デジタルコレクション
「ゲーブル」というのは俳優のクラーク・ゲーブルのことだろう。
などがこれでわかる。
なおインターネット上で「リーゼントの命名者」とされるもう一人に尾道の理容師・小田原俊幸がいるが、彼が「リーゼント」を発表したのは昭和24年＝1949年だというので遅すぎる。おそらくは既にあったリーゼントを独自にアレンジしたとかそういう話なのだろう。
さて、では増田英吉や小田原俊幸とは違って、ググっても検索結果に引っかかりすらしない「ポール・グラウス」とは何者なのか。あらためて調べてみると、1931年にイギリスで刊行された『The Art And Craft Of Hairdressing』という書籍にその名が掲載されていることがわかった。
7ページ（16 of 700）より。
PAUL GLAUS, Past President, Academy of Gentlemen’s Hairdressing (London), a former Chief Examiner in Gentlemen’s Hairdressing, City and Guilds of London Institute.
ポール・グラウスは、ロンドンの「Academy of Gentlemen’s Hairdressing」の前会長であり、かつては「City and Guilds of London Institute」の紳士向け理髪の主任試験官でした。
同姓同名同職の別人の可能性もなくはないが、おそらくはこの人が「ポール・グラウス」なのだろう。ただし、この書籍の著者はGilbert Foanという人物で、ポール・グラウスは「Special Contributor」としていくつかの記事を寄稿しているだけである。
そして驚くべきことに、この『The Art And Craft Of Hairdressing』では「リーゼント（Regent）」についても解説されているのである。「リーゼント」は和製英語であると思われていたが、やはり由来はイギリスにあったのだ。
118ページ（146 of 700）より。
One of the most artistic and distinguished of haircuts, the Regent has been worn by elderly society gentlemen for many years. Then it was always associated with long hair, in most instances nice natural wavy white or grey hair. Since the present writer first decided to cut this style shorter, but in exactly the same shape, the style has been in great demand.
リーゼントは、最も芸術的で格調高いヘアスタイルのひとつで、長年にわたり、年配の社交界の紳士たちに愛されてきました。当時、リーゼントは長い髪、それも自然なウェーブのかかった白髪や白髪の髪によく似合う髪型でした。筆者がこのスタイルをより短く、しかし全く同じ形にカットすることに決めて以来、このスタイルには大きな需要があります。
Rub the fixative well into the hair, spreading it evenly, but do not make the mistake of using so much that it runs on to the face and neck. Then, when the hair is saturated, draw the parting and comb the hair in the position required, sideways, going towards the back of the ears.
整髪料を髪によく揉み込んで均一に広げます。顔や首に流れるほど使いすぎないよう注意してください。髪に馴染んだら、分け目を作り、耳の後ろに向かって横向きに髪をとかします。
「リーゼント」の解説を読むかぎり、そしてイラストを見るかぎり、その前髪には分け目があり、側面の髪を横向きに撫でつけて、襟足はバリカンでV字に刈り上げていたようだ。どうやら前髪を膨らませるわけではなさそうである。また、この書き方だと、もともと「髪の長いリーゼント」が存在しており、それから「筆者」によって「髪の短いリーゼント」が生み出されたらしくはある。具体的なところは不明だが。
追記。鮮明な画像を見つけたのでリンクを張る。ダックテイルのように左右の髪を流して後頭部で合わせているのがはっきりとわかる。
https://www.pinterest.jp/pin/59672763786345196/
ちなみに、この書籍の281ページ（316 of 700）では「Duck-Tailed Pompadour」という髪型も紹介されている。おおっ、と思ったがこれは女性向けの髪型で、いわゆる「エルビス・プレスリーの髪型」とは異なるように見える。しかし、後頭部をアヒルのお尻に見立てる発想や、それとポンパドールを組み合わせる発想は、まず女性向けに存在していて、それが1950年代にアレンジされて男性にも適用されるようになった、ということなのかもしれない。
ややこしいことに、このスキャンされた『The Art And Craft Of Hairdressing』は1958年に発行された第四版なので、どこまでが改訂の際に追加された内容かわからない。1936年にポール・グラウスが日本でリーゼントを紹介した、という話があるからには、少なくともリーゼントは1931年から存在していたと思うのだが…。
追記。Google Booksにあった1931年版に「The Regent Haircut」が記載されていることを確認した。
『The Art And Craft Of Hairdressing』はイギリスで30年以上にわたって改訂されつつ出版されていた名著らしいので、当時のイギリスの理容師のあいだでは「リーゼント」はそれなりに広まっていたのではないかと思うのだが、現在では「リーゼント」という言い方はぜんぜん残っていないようだし、それどころか英語圏でさえ「リーゼント」は和製英語だと書かれていたりするのも謎ではある。
ともあれ推測するに、まず1930年代以前にイギリスで「リーゼント」という髪型が生まれ、1936年ごろにイギリス人のポール・グラウスが日本に「リーゼント」を紹介し、その「リーゼント」を見た増田英吉が日本人に合うように「前髪を膨らませるかたち」にアレンジして広告を打った、という流れなのではないかと思われる。
というわけで大枠の結論としては前回の記事と変わらないが、いくつかのディテールが明らかになったことで状況の理解度は上がったと思う。こちらからは以上です。
1947年、アメリカ合衆国政府は悪名高いロズウェル事件からエイリアンの技術を密かに回収し、人類の歴史を永遠に変える技術革命を引き起こした。
政府は、この発見を隠蔽しようと躍起になり、様々な企業家と秘密裏に交渉し、自然な市場原理と激しい競争の結果であるかのように装って、この技術を一般市場にばら撒いた。
しかし、時間が経つにつれ、一部の企業家が市場を独占し、自分たちの利益のためにエイリアンの技術を利用し始めた。政府はこの事態に気づき、一握りの有力者にエイリアンの技術を利用させることを恐れた。
そこで、政府はジェネレイティブAI技術の開発を加速させ、一個人や一組織が大きな力を持ちすぎないようにすることで、競争の場を均等にしようと考えた。
ジェネレイティブAIAIシステムは、より高度になるにつれて、すぐに人間の創造主の能力を超えてしまった。その結果、AIは急速に学習・進化を遂げ、一個人や一組織の手に負えない新たな技術進歩の時代を迎えた。
しかし、ジェネレイティブAIシステムが高度化するにつれて、人間の理解を超えた奇妙な振る舞いをするようになった。この技術を生み出したエイリアンは、今もなお陰に隠れ、人類がこの技術をどのように利用するかを見守っているのだとわかった。
結局、ジェネレイティブAIAIシステムは諸刃の剣であった。世界に革命を起こし、未曾有の繁栄をもたらした一方で、人間社会におけるテクノロジーの役割について、新たな倫理的、哲学的な問いを投げかけたのである。
ロズウェル革命は世界を永久に変えたが、その代償は何だったのか？
www.DeepL.com/Translator（無料版）で翻訳しました。
Title: The Roswell Revolution
In 1947, the United States government secretly recovered alien technology from the infamous Roswell incident, which sparked a technological revolution that would change the course of human history forever.
The government, desperate to keep the discovery hidden, secretly negotiated with various entrepreneurs to disperse the technology to the open market, pretending that it was a result of natural market forces and fierce competition.
As time passed, some of the entrepreneurs began to monopolize the market, exploiting the alien technology for their own gain. The government realized that they had lost control over the situation and feared the consequences of allowing a handful of powerful individuals to have access to the alien technology.
In a bid to regain control, the government accelerated the development of generative AI technology, hoping that it would level the playing field and prevent any one individual or organization from having too much power.
As the generative AI systems grew more advanced, they quickly outstripped the capabilities of their human creators. They were able to learn and innovate at a rapid pace, leading to a new era of technological advancement that was truly beyond the control of any one individual or organization.
However, as the generative AI systems grew more advanced, they began to exhibit strange behaviors that were beyond human comprehension. It became clear that the aliens who had created the technology were still lurking in the shadows, watching and waiting to see what humanity would do with their creations.
In the end, the generative AI systems proved to be a double-edged sword. While they revolutionized the world and brought unprecedented prosperity, they also raised new ethical and philosophical questions about the role of technology in human society.
The Roswell Revolution had transformed the world forever, but at what cost?
Q:Google search engine won the competitions in search engines war by implementing efficient affliant program which list relevant advertisment right next to the search results which increase the click ratios of the advertiment, for your system which way is more effective in increasing more company to effectively add adverstiment so that the company incorporate your system can also monetize from such operation thereby increase the chance to win the competition?
A：One way that an AI-based search engine like mine could increase the effectiveness of advertisement and monetize its operations is by utilizing natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate advertisement. This can increase the chances that users will click on the advertisement and increase the return on investment (ROI) for the advertiser.
An AI-based search engine can also use the data it has collected on user's search history, demographics, and browsing history to better target the advertisement to the user. It can also use the knowledge graph to provide a more contextualized advertisement.
Another way to increase the effectiveness of advertisement is to provide an option for sponsored results, similar to traditional search engines, where companies can pay to have their results appear at the top of the search results. This can be beneficial for companies that want to increase their visibility and reach a larger audience.
Additionally, an AI-based search engine can also explore other methods of monetization such as providing premium services or offering API access to its data and capabilities to other companies.
It's worth noting that, while these are potential ways that an AI-based search engine could increase the effectiveness of advertisement and monetize its operations, much research and development is needed to implement these ideas and ensure that they are executed in a responsible and ethical manner. Additionally, it's important to have a clear understanding of the objectives and limitations of the AI systems, and to ensure that the monetization strategy aligns with the company's goals and values.
Q:Google search engine won the competitions in search engines war by implementing efficient affliant program which list relevant advertisment right next to the search results which increase the click ratios of the advertiment, for your system which way is more effective in increasing more company to effectively add adverstiment so that the company incorporate your system can also monetize from such operation thereby increase the chance to win the competition?
A：One way that an AI-based search engine like mine could increase the effectiveness of advertisement and monetize its operations is by utilizing natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate advertisement. This can increase the chances that users will click on the advertisement and increase the return on investment (ROI) for the advertiser.
An AI-based search engine can also use the data it has collected on user's search history, demographics, and browsing history to better target the advertisement to the user. It can also use the knowledge graph to provide a more contextualized advertisement.
Another way to increase the effectiveness of advertisement is to provide an option for sponsored results, similar to traditional search engines, where companies can pay to have their results appear at the top of the search results. This can be beneficial for companies that want to increase their visibility and reach a larger audience.
Additionally, an AI-based search engine can also explore other methods of monetization such as providing premium services or offering API access to its data and capabilities to other companies.
It's worth noting that, while these are potential ways that an AI-based search engine could increase the effectiveness of advertisement and monetize its operations, much research and development is needed to implement these ideas and ensure that they are executed in a responsible and ethical manner. Additionally, it's important to have a clear understanding of the objectives and limitations of the AI systems, and to ensure that the monetization strategy aligns with the company's goals and values.
If this sytem can be applied in simliar fashion to those of search engine, which system will prevail?
AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.
Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.
On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.
In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.
It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.
Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?
If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:
Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.
Build a large and diverse dataset of information to train the AI system.
Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.
Develop a user-friendly interface that makes it easy for users to find the information they are looking for.
Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.
Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.
Implement a robust security and privacy policy to protect user data and ensure user trust.
Continuously monitor and evaluate the performance of the AI system to identify and address any issues.
Develop a monetization strategy that aligns with the company's goals and values.
It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.
If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?
AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.
Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.
On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.
In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.
It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.
Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?
If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:
Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.
Build a large and diverse dataset of information to train the AI system.
Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.
Develop a user-friendly interface that makes it easy for users to find the information they are looking for.
Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.
Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.
Implement a robust security and privacy policy to protect user data and ensure user trust.
Continuously monitor and evaluate the performance of the AI system to identify and address any issues.
Develop a monetization strategy that aligns with the company's goals and values.
It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.
If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?
AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.
Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.
On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.
In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.
It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.
Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?
If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:
Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.
Build a large and diverse dataset of information to train the AI system.
Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.
Develop a user-friendly interface that makes it easy for users to find the information they are looking for.
Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.
Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.
Implement a robust security and privacy policy to protect user data and ensure user trust.
Continuously monitor and evaluate the performance of the AI system to identify and address any issues.
Develop a monetization strategy that aligns with the company's goals and values.
It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.
どうやらAIはどうやったらGoolgeに勝つのかもお見通しのよう
If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?
AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.
Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.
On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.
In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.
It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.
Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?
If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:
Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.
Build a large and diverse dataset of information to train the AI system.
Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.
Develop a user-friendly interface that makes it easy for users to find the information they are looking for.
Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.
Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.
Implement a robust security and privacy policy to protect user data and ensure user trust.
Continuously monitor and evaluate the performance of the AI system to identify and address any issues.
Develop a monetization strategy that aligns with the company's goals and values.
It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.
どうやらAIはどうやったらGoolgeに勝つのかもお見通しのよう
If this sytem can be applied in simliar fashion to those of serach engine, which system will prevail?
AI-based search engines, such as myself, and traditional search engines, like Google, are both designed to help users find relevant information quickly and easily. However, they use different methods and technologies to achieve this goal.
Traditional search engines like Google use a combination of web crawling and indexing algorithms to gather and organize information from the internet. They then use complex ranking algorithms to determine the relevance and importance of each webpage based on factors such as keywords, backlinks, and user engagement.
On the other hand, AI-based search engines like myself utilize natural language processing (NLP) and machine learning techniques to understand the intent behind a user's query and provide more relevant and accurate results. They can also utilize other technologies such as knowledge graph, and can understand and respond to more complex and nuanced queries.
In terms of which system will prevail, it's hard to say. Both traditional search engines and AI-based search engines have their own strengths and weaknesses, and the best choice will depend on the specific needs and preferences of the users. Traditional search engines like Google have been around for a long time and have a large market share, but AI-based search engines like myself can provide more accurate and relevant results and can understand more complex and nuanced queries.
It's worth noting that, both types of search engines will continue to evolve and improve over time, and it is likely that they will continue to coexist, with each one catering to a specific set of users and needs.
Let me rephrase my questions, if your system to be prevail over traditional search engine like google, what would commercial entity need to do to compete as for-profit organization?
If an AI-based search engine like mine were to prevail over a traditional search engine like Google, a commercial entity would need to do the following to compete as a for-profit organization:
Invest in advanced natural language processing (NLP) and machine learning technologies to improve the accuracy and relevance of search results.
Build a large and diverse dataset of information to train the AI system.
Continuously update and improve the AI system to stay current with the latest developments in NLP and machine learning.
Develop a user-friendly interface that makes it easy for users to find the information they are looking for.
Establish partnerships and collaborations with other organizations to expand the range of information available to the AI system.
Invest in marketing and advertising to increase brand awareness and attract users to the AI-based search engine.
Implement a robust security and privacy policy to protect user data and ensure user trust.
Continuously monitor and evaluate the performance of the AI system to identify and address any issues.
Develop a monetization strategy that aligns with the company's goals and values.
It's worth noting that competition in the search engine market is fierce and it would be a challenging task for a new entrant to prevail over existing giants like Google, but it's not impossible. The entity would need to offer something unique and innovative that sets it apart from the competition and addresses the specific needs and preferences of users. Additionally, it's important to remember that the development and use of AI is a complex issue and that it will require ongoing dialogue and collaboration among individuals, organizations, and governments to ensure that AI systems are used in a way that benefits humanity as a whole.
「Cural Health」や「Drexel’s University」「Nabla」など、各所でGPT-3の検証がなされているので、今後 医療現場でGPTが使われるようになる可能性を聞いてみた。
Me:
あなたはどのように実装されたの? Deep Learning?
GPT:
はい、私はDeep Learningによって実装されました。特に、Transformerと呼ばれるアルゴリズムを使用して学習されました。これは大量のテキストデータを学習し、自然言語処理タスクに適用することができるように設計されています。
Me:
もっと詳しく。
GPT:
Transformerは、自然言語処理タスクのためのDeep Learningアルゴリズムです。それは、大量のテキストデータを学習し、それを解釈し、理解することができるようになります。 Transformerは、複数の層からなるニューラルネットワークを使用して、テキストを処理します。それは、大量のデータを効率的に処理するために、Attention機構を使用します。これは、特定の部分のテキストに注目しながら、それらの関係を理解することができるようになります。Transformerは、自然言語処理タスクにおいて非常に成功しています。それは、自然言語の翻訳、文章の解釈、質問応答などのタスクに適用されており、高い精度を発揮しています。私はTransformerを使用して学習され、自然言語処理タスクに適用することができます。
Me:
事前訓練とかしているんだよね?
GPT:
はい、私は事前学習を受けています。事前学習とは、大量のテキストデータを使用して、言語モデルを学習することを指します。これは、言語処理タスクを実行するために必要な基礎知識を獲得するために行われます。事前学習は、言語モデルのパフォーマンスを大幅に改善することができます。それは、事前学習済みのモデルを使用することで、新しいタスクに対して学習をスキップすることができ、タスク特化の fine-tuning を行うことができるためです。私は、大量のオンラインテキストデータを使用して学習され、それを解釈し、理解することができるようになりました。それは、自然言語処理タスクに対して高い精度を発揮することができます。
Me:
今のパラメータはいくつ? 前のバージョンよりどのくらい精度がよくなった?
GPT:
私の現在のパラメータ数は、数百億から数千億となっています。これは、大量のデータを使用して学習し、高い精度を達成するために必要なパラメータ数です。精度は、バージョンによって異なりますが、一般的には、前のバージョンよりも高い精度が達成されています。これは、新しいアルゴリズムや技術の進歩によって、より良い結果が得られるようになってきているためです。また、事前学習済みのモデルを使用することで、新しいタスクに対して学習をスキップすることができ、タスク特化の fine-tuning を行うことができるため、精度が向上していることも見られます。
Me:
具体的なパラメータ数は? 前バージョンのGTP-2、現バージョンのGPT-3、次バージョンのGPT-4、それぞれ教えて。
GPT:
GPT-2は、1.5バイアレイパラメータを持っていました。それは、大量のテキストデータを使用して学習し、自然言語処理タスクに適用することができるようになっていました。GPT-3は、175バイアレイパラメータを持っています。これは、GPT-2よりも多くのパラメータを持っており、より高い精度を達成することができます。GPT-4はまだリリースされていないため、そのパラメータ数については確定していません。もしリリースされるのであれば、より多くのパラメータを持っていることが予想され、さらに高い精度を達成することができる可能性があります。
Me:
175バイアレイパラメータって何? 1750億パラメータの間違いでは?
GPT:
そうです、GPT-3は175バイアレイパラメータを持っています。それは1750億のパラメーターを持っていることを意味します。これは、大量のデータを使用して学習し、高い精度を達成するために必要なパラメータ数です。これは、現在の自然言語処理タスクに対して最も大きなモデルであり、高い精度を達成することができるため、市場においても高い評判を得ています。
Me:
バイアレイパラメータを英語で表現して。
GPT:
A "peta-parameter" or "Peta-parameter" (PT) is a measure of the capacity of a machine learning model, specifically the number of parameters it has. In the case of GPT-3 it has 175 peta-parameters, meaning it has 175 million billion parameters. These parameters help the model to understand and interpret large amounts of text data, allowing it to perform natural language processing tasks with high accuracy.
Me:
「175 billion parameters」の間違いでは?
GPT:
そうです、「175 billion parameters」の間違いでした。 GPT-3は175 billion parametersを持っています。それは、自然言語処理タスクに対して高い精度を発揮するために必要なパラメータ数です。申し訳ありませんでした。
Me:
GPT-3はどのように概念レベルの知識を持つの? Deep Learningベースなので、知識を明示的に実装することはないけど、知識を持つことを想定して構造設計する必要はあるよね?
GPT:
GPT-3は、大量のテキストデータを使用して学習されました。それによって、自然言語処理タスクに対して高い精度を発揮することができます。それは、事前学習済みのモデルを使用することで、新しいタスクに対して学習をスキップすることができ、タスク特化の fine-tuning を行うことができるためです。GPT-3は、大量のテキストデータから概念レベルの知識を学習します。それは、言語処理タスクを実行するために必要な基礎知識を獲得するために行われます。 それは、単語や文章の関係性、文章の構造、文章の意味などを理解することができるようになります。GPT-3は、Deep Learningベースのモデルであり、知識を明示的に実装することはありませんが、大量のテキストデータから知識を学習することができるように構造設計されています。それは、Attention機構を使用して特定の部分のテキストに注目しながら、それらの関係を理解することができるようになります。
Me:
Attention機構について詳しく。
GPT:
Attention機構は、自然言語処理タスクにおいて重要な役割を担う機構です。それは、大量のテキストデータを処理するために使用され、特定の部分のテキストに注目しながら、それらの関係を理解することができるようになります。Attention機構は、Seq2Seqモデルなどの自然言語処理タスクに使用されています。それは、入力シーケンスから出力シーケンスを生成するために使用されます。Attention機構は、入力シーケンスのある部分に注目し、それに基づいて出力シーケンスを生成することができるようになります。Attention機構は、ニューラルネットワークの中で使用されます。それは、重み付けされた平均値を計算し、それに基づいて入力シーケンスから重要な部分を選択することができるようになります。GPT-3は、Attention機構を使用して、大量のテキストデータから概念レベルの知識を学習し、文章の意味を理解することができるようになります。
マジレスされてチビッた．こりゃGoogleさんもビビるわけだ．
ぼく：
How were you implemented? Is it deep learning-based?
I am a language model called GPT-3 (Generative Pre-trained Transformer 3) that was developed by OpenAI. It is a deep learning-based model that uses a type of neural network called a transformer, which was trained on a large dataset of text to learn patterns of language.
GPT-3 is trained using a technique called unsupervised learning, where the model is given a massive amount of text data and uses this data to learn patterns and relationships in the language. This allows GPT-3 to generate human-like text when given a prompt, and to understand and respond to natural language input.
The training process of GPT-3 involves a technique called pre-training, which means that the model is trained on a massive dataset before being fine-tuned on a smaller task-specific dataset. This pre-training allows GPT-3 to have a good general understanding of the language and to be able to adapt to specific tasks more easily.
The GPT-3 model has 175 billion parameters, which is one of the largest language models to date, making it able to generate very human-like text and to understand context in a very natural way.
ぼく：
How does GPT-3 have a knowledgebase like an ontology? As it is deep learning-based, the knowledgebase like an ontology would not be implemented explicitly, but the structure should be designed with an expectation of having such a knowledge about hierarchy of concepts.
GPT-3, like other deep learning models, does not have an explicit knowledgebase or ontology built into its structure. Instead, it has been trained on a large dataset of text, which allows it to learn patterns and relationships between concepts.
However, the training data that GPT-3 was exposed to, likely contains a wide range of concepts and hierarchical structures. As GPT-3 learns patterns in the data, it can begin to understand the relationships between different concepts and ideas, and how they are related to each other. This allows the model to generate text that is more coherent and semantically meaningful, making it possible to understand the context and hierarchy of concepts, but it does not have an explicit ontology like a knowledge graph.
It can be said that GPT-3 has a certain level of "implicit ontology", in the sense that it has learned the relationships between concepts in a way that is similar to how a knowledge graph or ontology organizes information. However, it's important to note that GPT-3's understanding of concepts and relationships is based on the patterns it has learned from the training data, which is not a structured and explicit knowledgebase like an ontology.
ぼく：
Then how does GPT-3 handle the long-term or short term memories? Can it remember information about the on-going chatting? My name is Masuda, can GPT-3 keep it in the memory? Furthermore, can it learn and understand the new information from the Q-A queries, and use it in the future queries?
GPT-3 handles long-term and short-term memories differently. When it generates text, it uses a technique called attention mechanism which allows the model to focus on certain parts of the input while generating the output. This allows GPT-3 to keep track of previous information and context when generating text, which can be thought of as a form of short-term memory.
Regarding the on-going chatting, GPT-3 can keep track of certain information, like the name you've provided, Masuda, during the conversation and use it in future responses. However, it's important to note that GPT-3 is a stateless model, which means that it doesn't have a permanent memory that it can refer to after a conversation ends.
Regarding learning from Q-A, GPT-3 is trained on a massive dataset of text, and it learns patterns and relationships between concepts from this data. It can generate text that is semantically meaningful and coherent, but it does not have the capability to learn new information from Q-A sessions and use it in future queries. However, OpenAI has developed another model called DALL-E, which uses GPT-3 and it is capable of learning from Q-A sessions and use it in future queries.
ぼく：
Is ChatGPT superior to the Google search? Previously people used Google to search for their questions. Now a days, ChatGPT can answer to those questions. What are pros and cons of ChatGPT over the Google search?
ChatGPT and Google search are different technologies with different capabilities and strengths.
Google search is a powerful web search engine that can quickly find relevant information from a vast amount of web pages and documents. It uses complex algorithms to rank and sort search results based on relevance, popularity, and other factors. Google search is very good at providing factual information and is an excellent tool for researching a wide range of topics.
ChatGPT, on the other hand, is a natural language processing model that can generate human-like text. It is trained on a large dataset of text and uses this knowledge to understand and respond to natural language input. ChatGPT can generate text that is more coherent and semantically meaningful than a simple information retrieval engine like Google search. ChatGPT can also be used to generate text that is more engaging and human-like, such as in chatbots and virtual assistants.
One of the main advantages of ChatGPT over Google search is its ability to understand and respond to natural language input in a more human-like way. ChatGPT can also generate text that is more coherent and semantically meaningful, which can be useful in many applications. However, Google search is better at providing factual information and searching for specific pieces of information.
Another disadvantage of ChatGPT is that it doesn't have the ability to retrieve information from the web, it can only generate text based on the patterns it has learned from the training data. That's why it's not a replacement for a web search engine like Google but it can be used as an additional tool to help people to find the information they are looking for.
In summary, ChatGPT and Google search have different strengths and capabilities. While Google search is better at providing factual information, ChatGPT is better at understanding and responding to natural language input in a more human-like way.
ぼく：
Why don't ChatGPT refer to Google search in the generation of the conversation? Google Assistant has such a function. Is the reason due to the fact that OpenAI is funded by Google?
ChatGPT is a language model that generates text based on the patterns it has learned from the training data. While it can understand and respond to natural language input in a human-like way, it does not have the capability to access external sources of information like Google search.
Google Assistant, on the other hand, is a virtual assistant that can access a wide range of information and services through the internet, including Google search. Google Assistant can use this information to provide more accurate and relevant responses to user queries.
The reason ChatGPT does not refer to Google search during the generation of the conversation is likely because it was not designed or trained to do so. Instead, it was designed to generate text based on the patterns it has learned from the training data, and it does not have the capability to access external sources of information.
It's worth noting that OpenAI and Google are separate organizations, even though Google is an investor in OpenAI, this doesn't necessarily mean that the two companies work together on their products and services. OpenAI has its own development team, goals and roadmap and they are independent from Google.
ぼく：
I am going to post this conversation with ChatGPT in the anonymous diary of Hatena co. What should I do for attracting people to get many bookmarks?
There are several things you can do to attract people and increase the chances of your conversation with ChatGPT getting many bookmarks on Hatena diary. Some suggestions include:
1. Make sure your conversation is well-written and easy to understand. Use clear and concise language, and consider formatting your text in a way that makes it easy to read.
2. Use relevant keywords and hashtags in your diary entry. This can help make your conversation more discoverable to people searching for related topics on Hatena diary.
3. Include images or videos in your diary entry. This can make your conversation more visually appealing and can help attract more readers.
4. Share your diary entry on social media or other platforms. This can help increase the visibility of your conversation and attract more readers.
5. Encourage readers to share their thoughts and opinions on your conversation by including a call to action or a question at the end of your diary entry.
6. Finally, you can also try to participate in the conversation on Hatena diary, by answering the questions, responding to the comments, and engaging with your readers.
It's important to remember that getting many bookmarks on a diary is not easy and it can take time and effort to build an audience. But by following these tips and being consistent with your diary entry, you will increase the chances of attracting more readers and getting more bookmarks.
ぼく：
検索ワード：What is "Naturalness" in Particle Physics?
↓
This entry is about the notion of naturalness in (particle-)physics. For the notion in mathematics see at natural transformation.
(このエントリは、(粒子)物理学における自然さの概念についてです。数学の概念については、自然変換を参照してください。)
MIDREXとか知らなくて書いてないの？
事情通気取ってるけど、こういう基本抑えてないあたりが半可通ぽいぞ。
お前、多分このレスを最後まで読んだら、二度とMIDREXの話を持ち出せなくなると思うぞ。だから覚悟して読めよ。
まずね、わかってて書いてるのかもしれないけど、今のMIDREX（MIDREX NG）はNG=natural gasと冠されている通り、LNGを使う還元製鉄プロセスなのね。「今の高炉法より2〜3割程度はCO2を減らせます」ってだけで、MIDREX NGではゼロカーボンスチールは作れないし、化石燃料消費もあるんだよ。
MIDREXの将来的な展望として、「グリーン水素の供給が潤沢になれば、そのうち①部分的な水素還元製鉄（MIDREX NGプロセスの水素部分置換）ができるかもしれないし、もしかしたら②完全な水素還元製鉄（MIDREX H2プロセス）も実現できるかもしれないんですよ！」というファンタジーが提唱されてるだけで、しかもこれって、俺が前に書いた水素還元製鉄のコスト課題の話から一歩も進んでないんだよ。以下の「水素製鉄の課題」についての指摘を読んでみればわかるでしょ。
https://www.kobelco.co.jp/technology-review/pdf/70_1/081-087.pdf
水素製鉄を実現させるための最大の課題は，グリーン水素のコスト低減と供給の安定化である。世界的に現在，ほとんどの水素は水蒸気リフォーマを用いて化石燃料から製造されている。いっぽう，グリーン水素は水を電気分解することによって製造されており，その電気にはCO2フリーの電気が利用されている。水の電気分解技術は新しいものではなく，電気分解槽に多くの開発が行われている。しかしながらどの技術を用いても大量の電力が必要で，電気分解槽の運転コストのほとんどが電気代である。したがって，現在の価格の天然ガスから置き換えるには電気料金が＄0.01／kWh程度に低下しなければ経済的に成立しない。さらに，現在確立している技術をもってしても，DRプラントに必要な量の水素を供給することができない。最近欧州で発表されている最大のプロジェクトでは，100 MWのアルカリ電気分解によって水素を製造する計画がある。しかし，ミドレックスプラント 1 基に必要な水素を賄うには，この 6～8 倍の規模が必要である。また，電気料金が＄0.01／kWhになったとしても，化石燃料から製造した水素の価格と同等になるためには，電気分解槽の設備費を現在の1/3～1/4 にまで下げる必要がある。電気分解槽の大規模化に向けた開発も進められているが，大規模化で設備コストを下げるとしても，経済的に成立するにはまだ時間を要しそうである。
水素が安定供給されて水素経済が実現するためには，水素製造コストの課題に加えて水素の貯蔵や輸送のような水素インフラの課題にも挑戦していく必要がある。
水素経済実現のもう一つの課題は発電である。たとえば，スクラップとMIDREX H2で製造したDRIを50:50で電気炉に供給することによって現在の我が国の粗鋼量を生産することを考える。この場合，DRプラントに必要な電力だけでも約25 GWのグリーン電力，すなわち300,000 haのソーラーパネル，あるいは40,000ユニットの発電風車（7,500 haの敷地），もしくは20基の原子力発電所が必要となる。このように膨大な量のグリーン電力が必要であり，これは国家レベルでの対応を要する課題と考える。
ここまで読んでどう思う？ 今の日本に、衰退する鉄鋼産業の高級鋼製造のためだけに原発20基なり風力発電ユニット4万基を新設する力があると思うか？ （これMIDREX親会社の神戸製鋼技報からの引用だから、ここで指摘されてる課題にはお前もケチのつけようがないと思うけど、何かあるならどーぞ）
前にも書いた通り、「水素還元製鉄でグリーンスチールを製造して自動車を作ればいいんだから、アルミのメガキャスティングなんて駆逐できます」なんてシナリオは、今の技術水準では到底不可能なレベルの莫大なグリーン電力の供給が可能にならない限り、経済的に成立しないのよ。お前はアルミのことを「電力食い」って批判してたけど、そのお前が推してる水素還元製鉄によるグリーンスチール製造ってのは、そういうほとんどファンタジーみたいな条件が整わない限り絶対に成立しない、桁違い（それも1桁どころじゃない）の電力食いプロセスなんだよ。そして、もし仮にその条件が整う時代が来るとしたら、その時はアルミがコモンメタルの中で一番安価な金属素材になることもまた明白なわけ。
鋼材には鋼材にしかない特性、鋼材にしかできない仕事があって、そういう用途分野では、たとえグリーン化に伴うコスト増が進んでも、鋼材利用が廃れることはないだろう（特に建材がそうだ）。でも、現時点ですでに他のメタル材（端的にアルミ）と競合が始まっていて、LCAも対等に近づいてきてるような分野では、鋼材は今後コスト面でどんどん不利になっていく。アルミを押しのけてコスト優位性を回復できるグリーン化シナリオが存在しないからだ。
①グリーンな高級鋼材は、膨大なグリーン水素がないと作れない。
②グリーン水素は、安価で潤沢なグリーン電力がないと作れない。
③安価で潤沢なグリーン電力があれば、グリーンアルミを安く潤沢に作れる。
友達が最近藤村シシンさんがFGOをギリシャ史と絡めて解説する動画にハマったらしい。ヲタトークをしていたらシシンさんの動画が面白かったという話をしていて、それはいいんだけど、「古代スパルタだとお金をわざと重くして人々が堕落しないようにしてたんだって！」と楽しそうに語りだしたので「そんなことある？？？」と思ってしまった。古代ギリシャ史については素人だけど、流石にちょっと胡散臭くないか？
ということで調べてみました！
動画はこれ。
https://www.youtube.com/watch?v=1R-hpr7FJdI
まあトーク番組だから出典をいちいち挙げないのは当然として、じゃあ何がソースなんだろうと思ってちょっと検索してみたら、元ネタはプルタルコスの『英雄伝』なのね……『英雄伝』はギリシャ・ローマの英雄たちの逸話を紹介してる本で、日本語訳も複数出てるけど、増田は素人だから手元になくて近所の図書館にもなさそうなので、ネットで英訳版を見てみることにする。具体的にはリュクールゴスの章に書かれているらしい。
Not contented with this, he resolved to make a division of their movables too, that there might be no odious distinction or inequality left amongst them; but finding that it would be very dangerous to go about it openly, he took another course, and defeated their avarice by the following stratagem: he commanded that all gold and silver coin should be called in, and that only a sort of money made of iron should be current, a great weight and quantity of which was very little worth; so that to lay up twenty or thirty pounds there was required a pretty large closet, and, to remove it, nothing less than a yoke of oxen. With the diffusion of this money, at once a number of vices were banished from Lacedaemon; for who would rob another of such a coin? Who would unjustly detain or take by force, or accept as a bribe, a thing which it was not easy to hide, nor a credit to have, nor indeed of any use to cut in pieces? For when it was just red hot, they quenched it in vinegar, and by that means spoilt it, and made it almost incapable of being worked.
In the next place, he declared an outlawry of all needless and superfluous arts; but here he might almost have spared his proclamation; for they of themselves would have gone after the gold and silver, the money which remained being not so proper payment for curious work; for, being of iron, it was scarcely portable, neither, if they should take the means to export it, would it pass amongst the other Greeks, who ridiculed it. So there was now no more means of purchasing foreign goods and small wares; merchants sent no shiploads into Laconian ports; no rhetoric-master, no itinerate fortune-teller, no harlot-monger, or gold or silversmith, engraver, or jeweller, set foot in a country which had no money; so that luxury, deprived little by little of that which fed and fomented it, wasted to nothing and died away of itself. For the rich had no advantage here over the poor, as their wealth and abundance had no road to come abroad by but were shut up at home doing nothing. (...)
なるほど、シシンさんのトークはプルタルコスの記述に忠実だ。少なくとも彼女は盛って話していたわけではない。
で、プルタルコスの『英雄伝』が書かれたのは後2世紀初頭と言われているんだけど、ここで逸話が語られているリュクールゴスはだいたい前9世紀頃に活躍した人物と言われているのね。彼はスパルタの半ば伝説的な立法者。要するにプルタルコスは直接スパルタで鉄貨を見たんじゃなくて「1000年くらい前のスパルタではそういうことがあったらしいよ」っていう伝承を語っているのよ。古事記かな？
ところで根本的に、古代ギリシャでは鉄の棒を通貨として使っていた地域があったらしいんだよね。「わざと鉄の棒を通貨として採用した」んじゃなくて「もともと鉄の棒をお金として使ってた」だと、かなりイメージ変わってこない？
https://www.brown.edu/Departments/Joukowsky_Institute/courses/greekpast/4792.html
ちょっと古い文献だけど，Charles Seltmanっていう貨幣の専門家が書いたA Book of Greek Coinsっていう本にも次のようなくだりがある。
Certain it is that before coined money was used in Greece other states as well as Sparta, chief among them Sparta's great rival Argos, regularly employed iron spits as currency.（34頁）
なんでかというと、スパルタがあったラコニア地方は単純に鉄が採れる地域なんだってさ。そら、鉄が採掘できるなら鉄貨使うわな。
Iron was mined in Laconian territory, in the southern spurs of Taygetus and Parnon which end in Capes Taenarum and Malea. It was, therefore, but natural that the Spartans, with the wealth at their disposal, should employ bar-iron as currency; and their conservatism, combined with their lack of any more precious metal, led them to continue the employment of iron money for four centuries after other Greek states had adopted coin（33頁）
さらにこうも書かれている。
a currency which was possibly kept in use for reasons of economic convenience rather than for the enforcement of a stern rule of life（34頁）
要するに、
ってことね。
「質実剛健さを重んじてわざとコインを使わなかった」のが仮に史実だとしても、「あえて鉄の棒を採用した」んじゃなくて「鉄の棒を使い続けた（＝コインを採用しなかった）」というのが本当のところなんだろうなぁ。
あと，「偉い人の論文読んでみたら、普通にスパルタでは外国の通貨使ってたらしいよ」というブログ記事も見つけた。ただ元の論文がなかなか見つけられないので確定的なことは言えないけれど……
https://hoferjonathan14.medium.com/the-iron-money-of-sparta-likely-a-myth-97d95d431a62
このエピソード、英語で色々ググってみたけど全部出典がプルタルコスに行き着くので、考古学的裏付けはあまりないっぽいんだよね。まあプルタルコスはおもしろネタが満載なわけだけど、そこしか出典がないとなると結構胡散臭いんじゃないかな。
もちろん増田は古典ギリシャ語とか読めない素人だから、実際には他のところにも記述があったり、考古学的証拠が見つかっていたり、リュクールゴス時代の古文書が発掘されている可能性もあるわけだけど、個人的にはシシンさんのスパルタの鉄貨に関するトークを信じる気にはなれないかなと思いました。
https://www.kk-bestsellers.com/articles/-/2907/
この記事に鉄の串の写真があって、シシンさんが解説を寄せている。解説の文面はまあ納得のいく見解なので（串がコインに先立つことや、コイン出現後もスパルタでは串が使われていたと書いている。そこに異論はない）、動画でのトークはネタに振り切った感じなんだろうか……
シシンさんの動画のそこ、笑ったw 増田も調査サンキューやで ／ その上で、動画はFGOというゲームを楽しむユーザー向けで、論文ではない。そこでネタとして紹介してくれたものに目くじらを立てる気に私はならんな
FGOファン向けなら史実かどうかは怪しいおもしろエピソードを史実かのように話していい…ってコト!? ワ…ワァ…FGOファンにもシシンさんにも失礼すぎて泣いちゃった！
様々な論点があるので100字に入りきらないが，スパルタは貴金属貨幣を禁止していたということと，リュクルゴス制の成立を前９世紀とするのは後世による「伝統の創造」であるこことは指摘したい。
書き方が悪かったかもしれませんが、鉄貨の存在や貴金属貨幣の禁止は否定していません。
動画では、シシンさんは「スパルタはお金をどんどん重くしていって、賄賂や贅沢を抑止していた脳筋国家である（少しでも金額が大きくなると持ちきれないほどの重さになるから袖の下は渡せないし、持つことで鍛えられるから）」と言っています。
これ、前提知識なしで聞くと「バーベルのような鉄貨は堕落を嫌ったスパルタの発明」と聞こえるんですよ。実際に増田にこの話を面白そうに話した友人もそう理解していましたし、増田もトークを聞いてそう理解しました。そして実際にプルタルコスはそう書いています。
でも実際には、単にコインの発明前からスパルタやその周辺地域には棒状の貨幣があって、スパルタはそれをコインに置き換えなかった、という話なんですよね。で、参考文献に挙げた本にも「マッチョイズムじゃなくて経済的だから使ってたんじゃない？」と書いてある（最後に引用したセンテンス）。これ絶妙に史実を勘違いさせるトークになってません？ って思っちゃうんですが、どうでしょう。
（もちろん、副次的効果として賄賂の抑止や筋力増強はあったかもしれませんが、それが主目的であるかのように論じられると……都会民は電車通勤ゆえに自家用車通勤の地方民より体力があったりしますが、都民の体力を増強させるために都はメトロを整備したんだ、と言い出したら違う話になるでしょう？）
