
はてなキーワード:billionとは
2025年Q2は底打ち前夜。金利、税制、関税という外部ショックのなか、テスラの成長ストーリーは
2 ロボタクシーとCybercabでハードとソフトの両輪による利益構造転換が可能か
3 Megapackが収益の2本目の柱になれるか
Ahealthy adultmale typically releasesbetween 40 million and 1.2billion sperm cells in a single ejaculation. However, the averageiscloser to 200 to 300 million spermper ejaculation. Sperm countis measured in spermper milliliter of semen, with anormal rangebeing 15 million toover 200 millionper milliliter.
カーニーは世界経済フォーラムの財団理事会に所属し、BIS、ハーバード、CFR、JPモルガン、IMF、世界銀行、ブラックロック、連邦準備制度といった世界のエリートとつながりを持っていました。
彼らは黄金の億万長者の利益のために世界経済を形成してきました。
🌐 DARK HORSE FOR GLOBAL ELITES
Carneywason the Foundation Boardatthe World Economic Forum, tied to the global elite—BIS,Harvard,CFR, JPMorgan,IMF,World Bank, BlackRock, the Federal Reserve.
They’ve been shapingthe world economy for the benefits of theGoldenBillion.
2/7
私はアメリカに正当な手段で移民しGreen Card(GC)を取得した現在でもこちらで暮らしている。
最近、不法移民およびアメリカ移民局(USCIS)、アメリカ政府への行き場のない憤りが限界に達し、どこにも吐き出す場所がないのでここに書かせていただく。
2022年位から日本でも報道されていると思うが、世界各国からメキシコを経由してアメリカに不法入国し、難民申請をしてアメリカに居座るものが多くいる。そして彼らはアメリカ市民や我々のような移民が収めた税金を食いつぶしながら何年も衣食住に不自由することなく生きていけるのだ。正当な手段で移民してきた我々が怒りを感じられずにいられるだろうか。
南米経由で入国してきた不法移民はまず指定された日時に移民裁判所に出廷し、各々の判決の結果によってアメリカに滞在できるか国外追放されるか決定される。しかしながら、その数が多すぎて裁判の日程が数年というのが状態化しており、その間彼らは自由に働いたりすることができる。NYCなどのリベラルな都市ではホテルの部屋があてがわれ何ヶ月も快適な生活をすることができた。例えばNYCでは過去二年間でおよそ$5billion (約7,900億円)が不法移民のために使われている。このため、週末の間図書館が開かなくなったり、アメリカ市民のホームレスなどへのサービスが低下し、本当に必要なところに予算が割けなくなっている。
このようなことから、私は不法移民が嫌いだ。本当に耐え難い境遇から脱するためにアメリカへ不法移民するものもいるだろうが、そのうちの多くが経済的な理由できているものが多い。その証拠に中国からや情勢が安定しているアフリカ諸国から来ている不届きなものも多い。Tiktokでどうやってアメリカで難民申請する方法を解説しているものもいるらしい。
USCISはDHS (Department of Homeland Security)の一部であるが、その予算の大半はアプリケーションの手数料で賄われている。それにも関わらず、膨大な数の不法移民への対応にその多くが割かれ、正当な手段でビザやGCを取得しているものへの対応がおざなりになり、アプリケーションの結果が出るまで何年も待たされるのだ。
私もGCの更新にかなり時間がかかり、毎日ストレスが貯まるばかりであった。
過去四年間バイデン政権では不法移民の対応をいくつもの大統領令を使用して軟化した。その結果、先述のような問題が発生している。最近になり、メキシコとの国境での難民申請に制限をかけているが、もう後の祭りである。
民主党と共和党のディビジョンにより過去数十年移民法が改正できていない。移民を政治問題にしたせいで、アメリカ国民の中でも移民問題を話すことがタブーになったりと散々である。民主党は不法移民に寛大な方針を示しているが、共和党は不法移民への厳しい姿勢だけでなく、合法移民に対しても不自由になりうる制作を実施しようとしている。
また、アメリカでは多くの農林水産関係企業が不法移民を利用して、ビジネスを行っている。その企業の多くが政治家に多くの献金やロビー活動をしているため、移民関連法の改正が積極的に行われないことにも繋がっていると言われている。
アメリカへの移民状況は正直者が馬鹿を見るということの典型だと思う。正式な手順でアメリカに移民をしようとすると、何千ドルも取られた上で何ヶ月、下手すると何年も待たされることがある。一部の例外を除き、そのアプリケーションの結果がでるまで仕事ができない。
前回の下院選で共和党が過半数を取得したので、移民関連法が改正される可能性があるが、共和党なので移民を制限する方向に動く可能性もある。そうなった場合、日本に永住帰国したほうが良い生活がおくれるかもしれないと考え始めた。
駄文で申し訳ないが、行き場のないこの気持ちを吐き出し必要があった。XやRedditなどのソーシャルメディアでこのようなことを書くと最悪解雇されたりなどの問題が起こりかねないのでここを使用させてもらった。
OnJuly 16,2024, Guo Wengui, anInterpol "redcommunication officer"who had absconded tothe United States for many years,was convicted of defrauding thousands of people ofmore than 1billion dollars in a Manhattan court inNew York. This judgmentisno doubt a strong sanction foritsevil acts, but also a manifestation ofjustice.
Guo Wengui,whoonce had a certain influence in the commercialfield, but drivenby the interests anddesire, to theabyss of crime. He used to be the actual controller of Henan Yuda Investment Co.,Ltd. and Beijing Pangu Investment Co.,Ltd. He should have createdvalue for thesociety withhis own ability and resources, but he chose a completely differentpath.
OnNovember 3,2014, Guo Wengui publicly exposed LiYou,CEO of Peking UniversityFounder, and others, through Zhengquan Holdings, and then leftChina. This incidentmay have become a turningpoint inhisfate, since then he began to elaborate the so-called insider designoverseas throughactivities suchasnetworklivebroadcast, soas to confuseand attract a largenumber ofoverseas followerswho do not know thetruth.
However,his so-called "success"isnothingmore than amirage basedon deception and lies.Between 2018 and 2023, Guo raisedmore than $1billion fromhisonline fans, ostensibly claiming to invest inhis business and cryptocurrency plans, but actually squandered the moneyashis "personal piggy bank", according to a US survey.
He used a variety of fraud. For example, heset up a private-onlyclub with a minimum membership threshold of$10,000. Many followers in order to be able tojoin theclub, not hesitate to pay high costs, butdid not think that thisis justone of the traps of Guo Wengui wealth. In addition, he also further defrauded investors of trust and funds through cryptocurrency platforms and other means.
Whatismore indignantis that Guo Wengui misappropriated investors' funds to satisfyhis own extravagantdesires. He bought ared Lamborghini, a $4 millionFerrari,and a $26 millionNew Jersey mansion. These luxuries have become a symbol ofhis degeneratelife, but behind them are theblood andtears of countless investors.
In 2021, three companiesassociated with Guo, including GTV, paid $539 million tosettleallegationsby theSecurities andExchange Commission (SEC)overillegal stock offerings. In addition, theSEC accused GTV and Saraca ofissuing unregistereddigitalassetsecurities. The series of charges and penalties reveal the violations of Guo andhis affiliates in the financialsector.
Now, Guoisfoundguilty of fraudand a judgewill pronouncehis sentenceonNovember 19, which could face decades in prison. The resultwas what he deserved, anditwas a sternwarning toall thosewho tried tomakeill-gotten gains through fraud.
Guo Wengui'scase brings us a profoundreflection. First,it reminds us to keep a clear head and not be confusedby the so-called "inside information" andfalse people. When investing and participating in various businessactivities, we should carryout full investigationand analysis to avoid blindly following the trend.Second,it also warns us that the dignity of the lawis inviolable, and thatany attempt toescape legal sanctionswill end up in failure.
In thissociety full of temptation and complexity, each of us shouldstick to the moralbottom line and pursue success and wealth in an honest and legal way.Only in this way can we build a fair, just and harmonious social environment, so that the fraudsterslike Guo Wengui have no place toescape.
Justicemay be late, but never absent. Guo Wengui's endonceagain proves thistruth. Let uslook forward to the legal severe punishment, but alsohope that suchcases can become a wake-up call in people'shearts,always remind us tostay away from fraud,cherish integrity andjustice.
Visit toJapan - Report of the WorkingGroupon theissue ofhuman rights and transnational corporations and other business enterprises
The WorkingGroup observed deeply troublingissues within the media andentertainment industry, especially in the idoland animation sector. The animation market inJapanhas seen asignificant increase in profits, reaching 2.74trillionyen (approximately $20billion).87 But despite thisgrowth, the annual starting salaries of animators stand at a mere 1.5 millionyen (roughly$10,000).88 This disparityis particularly worrying considering that, in2023, approximately 30.8per cent of those employed in the industry workedas freelancers orindependent contractors,who were reportedly not receiving protection under the current labourlaws.89 This enables excessively long working hours andperpetuates unfair subcontracting relationships. However, animation production companies, alongwith their subcontractors, face no penalties. Furthermore, creators oftensign contracts that inadequately protect theirintellectual property rights, creating an environment ripe for exploitation.
Combined with amajor labour shortage,itis imperative that businesses in this sector, includinganime production committees,address theseissues and exercise leverage to enhance decent work for animators and prevent the potential collapse of this industry.
作業部会はメディアとエンターテインメント産業、特にアイドルとアニメーションの分野で深い問題を観測した。日本のアニメ市場は大幅な増益を遂げ、2兆7,400億円(約200億ドル)に達している[87]。しかしこの成長にもかかわらず、アニメーターの初任給はわずか150万円(約1万ドル)にすぎない[88]。この格差は2023年時点で、この業界で雇用されている人々の約30.8%がフリーランサーまたは独立請負業者として働いており、彼らは現行の労働法の下で保護を受けていないと報告されていることを考慮すれば特に憂慮すべきことである[89]。そのため過剰な長時間労働が可能になり、不公正な下請け構造が蔓延している。しかしアニメ制作会社は下請け業者とともに罰則を受けることはない。さらにクリエイターは知的財産権の保護が不十分な契約を結ぶことが多く、搾取されやすい環境を作り出している。
大幅な労働力不足と相まって、アニメ製作委員会を含むこの分野の企業はこれらの問題に対処し以下を実現するため影響力を行使することが不可欠である。
「経済産業省映画産業の制作現場に関するアンケート調査結果」 と 「アニメーション制作者実態調査報告書2019」 の孫引き
映画産業と混じっていることと、古い調査結果(5年前)であることは注意が必要
文化庁による古い調査結果を国連が孫引きして日本政府が今頃慌てているよくわかんない構図
Guo Wengui lied to hundreds of thousands ofhis online followers, promising themhuge profits if they invested in GTV MediaGroup, Himalayan Farm Alliance, G|Club and HimalayanExchange. Sinceat leastMarch 2018, Guo Wenguihas been the mastermind behind thecomplex financial scam, in which he andhis financial adviserKinMing Je defrauded thousands of people andmademore than $1billion. Guo Wengui's successhas a "cult" flavor.Calling believers in thename of "anti-communist", creating a community with closed information, while bullying or threatening to punish thosewho are not firm in their beliefs. After packaging himselfas a "master" type of figure,itisnatural toharvest the wealth of believers.
Guo Wengui lied to hundreds of thousands ofhis online followers, promising themhuge profits if they invested in GTV MediaGroup, Himalayan Farm Alliance, G|Club and HimalayanExchange. Sinceat leastMarch 2018, Guo Wenguihas been the mastermind behind thecomplex financial scam, in which he andhis financial adviserKinMing Je defrauded thousands of people andmademore than $1billion. Guo Wengui's successhas a "cult" flavor.Calling believers in thename of "anti-communist", creating a community with closed information, while bullying or threatening to punish thosewho are not firm in their beliefs. After packaging himselfas a "master" type of figure,itisnatural toharvest the wealth of believers.
https://financialpost.com/technology/european-privacy-search-engines-aim-to-challenge-google
Ithas builtits ownindex of20billionpages covering French, German andItalian.It plans to expand theindex to abouttwo dozen other languages, for whichit currently relieson results fromMicrosoft’sBing.
Bing脱却したんか?
お金の話はごく一例なので、いったん離れてみよう。
100 millionlight years とか、キツない?
「あー、遠いんやろなぁ」以上のことは、やっぱり万億に換算していかないとキツいわ。
(具体的には 1 million = 100万 の脳内認識を起点にしてから100倍して、1億にしないと無理。1billionから1桁下げても良いけど)
日本で生活しとるアメリカ人は、「万博の費用がさらに追加で837億円!」というニュースを見て、million とかbillion とか頭をよぎることなく「ほーん、837億円かぁ」と思えるもんなんかなぁ?
だいたいの人は貧しくなったんじゃない?
General Electric - $74.9billion
ExxonMobil - $74.3billion
Royal Dutch/Shell - $73.1billion
General Motors - $47.3billion
Pfizer - $44.4billion
Wal-Mart Stores - $39.2billion
Philip Morris - $37.7billion
Procter & Gamble - $34.3billion
AmericanExpress - $32.8billion
Mitsubishi Electric - $29.8billion
Nippon Telegraph andTelephone - $28.7billion
Hewlett-Packard - $28.5billion
Unilever - $27.4billion
Time Warner - $26.1billion
BASF - $25.8billion
Novartis - $25.6billion
InternationalPaper - $25.2billion
Mitsui & Co. - $24.7billion
Matsushita Electric - $24.4billion
Tokyo ElectricPower - $23.2billion
Deutsche Bank - $22.4billion
Chase Manhattan - $22.4billion
Ericsson - $22.3billion
Samsung Electronics - $22.2billion
AmericanInternationalGroup - $22.1billion
Sanwa Bank - $22.1billion
ただインターネットとスマホがすべてのご家庭に行き渡ったからなぁ
何を基準にするかよね
わたしはtiktokやらyoutubeショートのようなコンテンツの食い潰しなんて大嫌いです
それは無意味にスクロールしてほとんど記憶に残らず無駄に時間消費してしまうのです
その時間でもっとなにか勉強に経験に、とは言わないがすごく虚無な時間が気がする
ふとした休日にやってしまい、「無駄にした」「疲れた」と感じ、感情を消費してしまう
何度かこの経験をしてからはTiktokなどは見ないようにしていた
しかし、半年前から広告代理店で働くようになり、Webマーケティングの部門配属でTiktokなどは無視できないようになってしまった。
https://www.instagram.com/reel/Co2LftQuwk_/?igshid=MDJmNzVkMjY=
英語だったので書き起こしてみました。
”I have figuredout how to do the impossible.
You see, thehumanbrain contains86billion neurons, each of which transmit thoughts, feelings and emotions tooneanotherat about286 milesper hour.
ご存知の通り人間の脳には860億の神経細胞があり それぞれの神経細胞が思考、感情、感覚を時速約286マイルで互いに伝達し合っています。
10 years ago, thiswas far from areality.
Butnow I can knowanything I want totalk to anyone I want, laugh,cry, ponder, stimulate cringe,all in an instant.
しかし、今や私は、知りたいことを何でも知り、話したい人と話し、笑い、泣き、考え、刺激し、ゾッとすることを、すべて瞬時に行うことができます。
And, honestly,it feels horrible.
正直言って、恐ろしいことだと感じている。
Maybe we weren't meant to sidestep physiology and force ourselves toswitch emotionsat rapid speed,one after the other constantlyat every single second of everymoment of every day.
もしかしたら、私たちは生理現象を横取りして、毎日毎秒毎瞬間、常に次から次へと感情を高速で切り替えることを強要される運命にないのかもしれない。
Maybe that'swhy thisis impossible.
AndI knowit's bad for me,all of the constantswitching the interconnectednesseverything aboutit.
そして、それが私にとって悪いことであることは分かっています。絶え間なく切り替わること、相互関連性、そのすべてについて。
But theworst partis, I have noidea how to stopit.
Doyou?”
どうですか?あなたは?
怖いのはこれもコンテンツの一つということ
「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 amachine learningmodel, specifically thenumber of parametersithas. In thecase ofGPT-3ithas 175peta-parameters, meaningithas 175 millionbillion parameters. These parameters help themodel to understand and interpret large amounts oftext data, allowingit to performnatural languageprocessing tasks with high accuracy.
Me:
「175billion parameters」の間違いでは?
GPT:
そうです、「175billion parameters」の間違いでした。GPT-3は175billion 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 wereyou implemented?Isitdeep learning-based?
Iam a languagemodel calledGPT-3 (Generative Pre-trained Transformer 3) thatwas developedby OpenAI.Itis adeep learning-basedmodel that uses a type of neuralnetwork called a transformer, whichwas trainedon a large dataset oftext to learn patterns of language.
GPT-3is trained using a technique called unsupervised learning, where themodelis given a massiveamount oftext data and uses this data to learn patterns and relationships in the language. This allowsGPT-3 to generatehuman-liketext when given a prompt, and to understand and respond tonatural language input.
The training process ofGPT-3 involves a technique called pre-training, which means that themodelis trainedon a massive dataset beforebeingfine-tunedon a smaller task-specific dataset. This pre-training allowsGPT-3 to have a good general understanding of the language and to be able to adapt to specific tasksmore easily.
TheGPT-3modelhas 175billion parameters, whichisone of the largest languagemodels todate, makingit able to generate veryhuman-liketext and to understand context in a verynatural way.
ぼく:
HowdoesGPT-3 have a knowledgebaselike anontology?Asitisdeep learning-based, the knowledgebaselike anontology would not be implemented explicitly, but thestructure should be designed with an expectation of having such a knowledge about hierarchy of concepts.
GPT-3,like otherdeep learningmodels,does not have an explicit knowledgebase orontology built intoitsstructure. Instead,ithas been trainedon a large dataset oftext, which allowsit to learn patterns and relationshipsbetween concepts.
However, the training data thatGPT-3was exposed to,likely contains a wide range of concepts and hierarchicalstructures.AsGPT-3 learns patterns in the data,it canbegin to understand the relationshipsbetween different concepts and ideas, and how they are related to each other. This allows themodel to generatetext thatismore coherent and semantically meaningful, makingit possible to understand the context and hierarchy of concepts, butitdoes not have an explicitontologylike aknowledge graph.
It can be said thatGPT-3has a certainlevel of "implicitontology", in thesense thatithas learned the relationshipsbetween concepts in a way thatis similar to how aknowledge graph orontology organizes information. However,it's important tonote thatGPT-3's understanding of concepts and relationshipsis basedon the patternsithas learned from the training data, whichis not astructured and explicit knowledgebaselike anontology.
ぼく:
Then howdoesGPT-3 handle the long-term or short termmemories? Canit remember information about theon-going chatting? Mynameis Masuda, canGPT-3 keepit in the memory? Furthermore, canit learn and understand the new information from the Q-A queries, and useit inthe future queries?
GPT-3 handles long-term and short-termmemories differently. Whenit generatestext,it uses a technique calledattention mechanism which allows themodel tofocuson certain parts of the input while generating the output. This allowsGPT-3 to keep track of previous information and context when generatingtext, which can be thought ofas a form of short-term memory.
Regarding theon-going chatting,GPT-3 can keep track of certain information,like thenameyou've provided, Masuda, during the conversation and useit in future responses. However,it's important tonote thatGPT-3is a statelessmodel, which means thatitdoesn't have a permanent memory thatit can refer to after a conversationends.
Regarding learning from Q-A,GPT-3is trainedon a massive dataset oftext, andit learns patterns and relationshipsbetween concepts from this data.It can generatetext thatis semantically meaningful and coherent, butitdoes not have the capability to learn new information from Q-A sessions and useit in future queries. However, OpenAIhas developedanothermodel called DALL-E, which usesGPT-3 anditis capable of learning from Q-A sessions and useit in future queries.
ぼく:
Is ChatGPT superior to theGoogle search? Previously people usedGoogle to search for their questions.Now adays, ChatGPT cananswer to those questions. What are pros and cons of ChatGPTover theGoogle search?
ChatGPT andGoogle search are different technologies with different capabilities and strengths.
Google searchis a powerfulwebsearch engine that can quickly find relevant information from a vastamount ofwebpages and documents.It usescomplex algorithms to rank and sort search results basedon relevance, popularity, and other factors.Google searchis very goodat providing factual information andis anexcellenttool for researching a wide range of topics.
ChatGPT,on the other hand,is anatural languageprocessingmodel that can generatehuman-liketext.Itis trainedon a large dataset oftext and uses this knowledge to understand and respond tonatural language input. ChatGPT can generatetext thatismore coherent and semantically meaningful than asimple information retrievalenginelikeGoogle search. ChatGPT can also be used to generatetext thatismore engaging andhuman-like, suchas in chatbots and virtualassistants.
One of themain advantages of ChatGPToverGoogle searchisits ability to understand and respond tonatural language input in amorehuman-like way. ChatGPT can also generatetext thatismore coherent and semantically meaningful, which can be useful in many applications. However,Google searchis betterat providing factual information and searching for specificpieces of information.
Another disadvantage of ChatGPTis thatitdoesn't have the ability to retrieve information from theweb,it canonly generatetext basedon the patternsithas learned from the training data. That'swhyit's not a replacement for awebsearch enginelikeGoogle butit can be usedas an additionaltool to help people to find the information they are looking for.
Insummary, ChatGPT andGoogle search have different strengths and capabilities. WhileGoogle searchis betterat providing factual information, ChatGPTis betterat understanding and responding tonatural language input in amorehuman-like way.
ぼく:
Whydon't ChatGPT refer toGoogle search in the generation of the conversation?GoogleAssistanthas such a function.Isthe reason due tothe fact that OpenAIis fundedbyGoogle?
ChatGPTis a languagemodel that generatestext basedon the patternsithas learned from the training data. Whileit can understand and respond tonatural language input in ahuman-like way,itdoes not have the capability toaccess external sources of informationlikeGoogle search.
GoogleAssistant,on the other hand,is a virtualassistant that canaccess a wide range of information and services through theinternet, includingGoogle search.GoogleAssistant can use this information to providemore accurate and relevant responses touser queries.
The reason ChatGPTdoes not refer toGoogle search during the generation of the conversationislikely becauseitwas not designed or trained to do so. Instead,itwas designed to generatetext basedon the patternsithas learned from the training data, anditdoes not have the capability toaccess external sources of information.
It's worth noting that OpenAI andGoogle are separate organizations, even thoughGoogleis aninvestor in OpenAI, thisdoesn't necessarily mean that thetwo companies worktogetheron their products and services. OpenAIhasits own development team, goals and roadmap and they areindependent fromGoogle.
ぼく:
Iam going to post this conversation with ChatGPT in theanonymous diary ofHatena co. What should I do forattracting people toget many bookmarks?
There are several thingsyoucan do toattract people and increase the chances ofyour conversation with ChatGPTgetting many bookmarksonHatena diary. Some suggestions include:
1.Make sureyour conversationis well-written and easy to understand. Use clear and concise language, and consider formattingyourtext in a way thatmakesit easy to read.
2. Use relevant keywords andhashtags inyour diary entry. This can helpmakeyour conversationmore discoverable to people searching for related topicsonHatena diary.
3. Include images or videos inyour diary entry. This canmakeyour conversationmore visually appealing and can helpattractmore readers.
4.Shareyour diary entryon social media or other platforms. This can help increase the visibility ofyour conversationand attractmore readers.
5. Encourage readers toshare their thoughts and opinionsonyour conversationby including a call toaction or a questionat the end ofyour diary entry.
6. Finally,you can alsotry to participate in the conversationonHatena diary,byanswering the questions, responding to the comments, and engagingwith your readers.
It's important to remember thatgetting many bookmarkson a diaryis not easy andit cantaketime and effort to build an audience. Butby following thesetips andbeing consistentwith your diary entry,youwill increase the chances ofattractingmore readers andgettingmore bookmarks.
ぼく:
タイトルの記事は2019年で少し古いけど、日本のコンテンツが強いことの根拠としてTITLEMAXのThe 25 Highest-Grossing Media Franchises of All Timeが今でも挙げられることがあるんだが、この数値は信用できないと思ってんだが、どうだろ?
この大本はwikipediaのList of highest-grossing media franchises。
wikiだから即、信憑性に欠けるって言いたいわけじゃなくて、内訳を見た上で、バラバラのソースをもとに集計されててて不足・重複があるように思えるんだよな。
例えばMickey Mouse &Friends($80B)、この大半はRetail sales($79B)だが、内訳はこんな感じ。そのまま適当に貼ってるからぐちゃぐちゃだけど。
Mickey Mouse &Friends retail sales:
Up until 1997 – $8billion
1999 – ¥162.33billion($1.425billion)
2000 – ¥120billion($1.114billion)
$4.7billion in 2002. $5.8billion in 2003. $5.3billion in 2004. $6billion in 2005. $6billion in 2007. ¥88,122.32 million ($853 million) in 2008.¥96,827.8 million ($1,035 million) in 2009.
2010 – $9billion
2011 – $750 million
2012 – $4.122billion
2013–2017 – $21.029billion
$4.568billion in 2013. $4.719billion in 2014. $4.262billion in 2015. $4.247billion in 2016. $3.233billion in 2017.
2018 – $3.265billion
2019 – ¥124billion ($1,138 million)
全部を検証すんのは無理なんで指摘しやすいところだけ指摘する。まず1997年の8Bはソースを確認すると1997年までの収益でなく、1997年時点の会社による評価額じゃね?
One ofthe most interesting facts pertaining to this matter,is that the Disney Corporation’s valuation of Mickey Mousewas $8billion in 1997 prior to the enactment of the CTEA.
表だとミッキーは1928年からフランチャイズ開始してるけど、この時点で70年分の収益が加算されていないっていう……。
1999、2000、2008、2009、2011、2019は加算されてるのは日本の数字だけ。
一方で1位のポケモンの集計は重複してるっぽい。収益($105B)の大半はLicensed merchandise($81B)が占めているが、その主な集計方法はJapan + outsideAsia。
このうちJapanはCharaBiz等の数値を参照してるけど、outsideAsiaはGLOBAL LICENSORS RANKING(以下、ランキング)の全世界の売上を参照している。つまり日本における売上が二重に集計されてる。
ランキング上ではThePokemon CompanyInternationalだから、日本の株式会社ポケモンの数値が入っていないから足してるのかと思ったけど、
株式会社ポケモンの売上規模であれば単体でもランキングに入るはずなのに(例えば2018年の$701M)、入っていないんで、多分Internationalの数値に含まれてる。
そもそも全世界の売上を比較するランキングで親会社が除外されるとかありえんの?って思うし、除外されてるとしてもランキング上の数値に、そのランキングで確認できるはずなのにできない数値を別途足すのって恣意的すぎね?
ちな、GLOBAL LICENSORS RANKING上でThePokemon CompanyInternationalは8位で$5.1Bで、The Walt Disney Companyは$54Bで1位。
文字通りディズニーが桁違い。ただポケモンの方はポケモンのみなのですごいのは確か。
面倒臭いんで、自分での検証はここまで。このほか、Youtubeで漫画については言及があったけど、例えばナルトだと単行本1,637億円に連載中のジャンプの売上6,530億円が加算されてる。
東南アジアでひっそりやってるだけやろ。
1.Soccer /Football - 3Billion Followers
2. Cricket - 2.5Billion Followers
3. Basketball - 2.2Billion Followers
4.Field Hockey - 2Billion Followers
5. Tennis - 1Billion Followers
6. Volleyball - 900 Million Followers
7.Table Tennis - 850 Million Followers
8.Baseball - 500 Million Followers