Movatterモバイル変換


[0]ホーム

URL:


はてラボはてな匿名ダイアリー
ようこそ ゲスト さんログインユーザー登録

「billion」を含む日記RSS

はてなキーワード:billionとは

次の25件>

2025-03-16

グロバリストとは?anond:20250316235101

スプートニク印度から

カーニーは世界経済フォーラム財団理事会所属し、BISハーバードCFRJP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

https://x.com/Sputnik_India/status/1900565302598943227

Permalink |記事への反応(1) | 23:52

このエントリーをはてなブックマークに追加ツイートシェア

2025-02-01

anond:20250201210751

Walkedout this morning,don'tbelieve what Isaw

A hundredbillion bottles washed upon the shore

Seems I'm notaloneatbeingalone

A hundredbillion castaways looking for ahome

Permalink |記事への反応(1) | 21:10

このエントリーをはてなブックマークに追加ツイートシェア

2024-12-26

不法移民への憤り

はじめに

私はアメリカに正当な手段移民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。

不法移民への憤り

2022年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理由できているものが多い。その証拠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難民申請する方法解説しているものもいるらしい。

USCISへの憤り

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、正当な手段ビザGCを取得しているものへの対応おざなりになり、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。

アメリカ政府への憤り

過去四年間バイデン政権では不法移民対応をいくつもの大統領令使用して軟化した。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制限をかけているが、もう後の祭りである

民主党共和党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不法移民に寛大な方針を示しているが、共和党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ロビー活動をしているため、移民関連法の改正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。

最後

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、共和党なので移民制限する方向に動く可能性もある。そうなった場合日本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。

Permalink |記事への反応(0) | 08:13

このエントリーをはてなブックマークに追加ツイートシェア

2024-10-22

Guo Wengui: The end of fraud and thetrial ofjustice

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.

Permalink |記事への反応(0) | 17:11

このエントリーをはてなブックマークに追加ツイートシェア

2024-10-18

国連日本アニメは「労働搾取」 ←これ

誰もソースを貼らないから調べたよ

報道機関ならちゃんと調べてくれよ

 

ソース: 

Visit toJapan - Report of the WorkingGroupon theissue ofhuman rights and transnational corporations and other business enterprises

 

指摘箇所

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.

作業部会メディアエンターテインメント産業特にアイドルアニメーションの分野で深い問題観測した。日本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わずか150万円(約1万ドル)にすぎない[88]。この格差2023年時点で、この業界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可能になり、不公正な下請け構造蔓延している。しか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。さらクリエイター知的財産権保護が不十分な契約を結ぶことが多く、搾取されやす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

アニメーターの decent work (意味:働きがいのある人間らしい仕事)を強化し、この産業崩壊を防ぐために。

注意:

経済産業省映画産業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

ソース

文化庁より委託をされた文化庁令和4年度メディア芸術連携基盤等整備推進事業調査研究

 

文化庁による古い調査結果を国連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

 

 

国連の報告よりも元ソースを見た方が詳しいし正確。年収は p46~ だけど全部読んだ方が良い

Permalink |記事への反応(1) | 12:03

このエントリーをはてなブックマークに追加ツイートシェア

2024-07-10

Portal

The Witness

Patrick'sParabox

noita

A=B

babaisyou

Understand

7Billion Humans

Permalink |記事への反応(0) | 19:26

このエントリーをはてなブックマークに追加ツイートシェア

2024-04-18

The Guo farmis a financial scam

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.

Permalink |記事への反応(0) | 16:21

このエントリーをはてなブックマークに追加ツイートシェア

2024-03-31

anond:20240331140513

その換算表いるか

と増えていくスケール

one

ten

hundred

thousand

million

billion

trillion

と増えていくスケールがあるだけじゃん?

日本にしたって単位に〇〇万円とかカン依存だと困る場合もあるし

単に数字読み慣れてないだけだと思うけどなあ

Permalink |記事への反応(0) | 14:15

このエントリーをはてなブックマークに追加ツイートシェア

2024-02-04

The Guo farmis a financial scam

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.

Permalink |記事への反応(0) | 13:56

このエントリーをはてなブックマークに追加ツイートシェア

2023-12-11

anond:20231211201757

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?

Permalink |記事への反応(0) | 20:19

このエントリーをはてなブックマークに追加ツイートシェア

2023-11-30

anond:20231130110433

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)

Permalink |記事への反応(1) | 11:25

このエントリーをはてなブックマークに追加ツイートシェア

anond:20231130101701

日本生活しとるアメリカ人は、「万博費用さらに追加で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?

Permalink |記事への反応(1) | 10:51

このエントリーをはてなブックマークに追加ツイートシェア

英語をいちいち頭の中で日本語翻訳しなくても読み聞きできるようになってきたけどさ、

数字だけはいまだに日本語日本円に変換しないとピンと来ないわ。

$10billion という字面を見て、

まずbillion10であることを認識して、

さら10billion100億になることを認識して、

ドルから1000億、1兆、と2桁追加して、

為替に応じて 1.5兆円 と換算して、

やっと感覚を合わせることができる。

まぁ、為替についてはヤードポンドとかも同じでしゃーないんだけど、thousand millionbilliontrillion を、千万億兆が頭によぎりもせず感覚で捉えられるようになるのは、相当難しそう。

Permalink |記事への反応(1) | 10:13

このエントリーをはてなブックマークに追加ツイートシェア

2023-04-12

anond:20230412203130

だいたいの人は貧しくなったんじゃない?

1993年時価総額ランキングこんな感じやぞ

 

General Electric - $74.9billion

ExxonMobil - $74.3billion

Royal Dutch/Shell - $73.1billion

AT&T - $70.9billion

IBM - $66.6billion

Ford - $57.4billion

Toyota - $50.6billion

General Motors - $47.3billion

DuPont - $46.8billion

Coca-Cola - $45.9billion

Pfizer - $44.4billion

Merck - $42.6billion

Microsoft - $40.9billion

Wal-Mart Stores - $39.2billion

Philip Morris - $37.7billion

Siemens - $37.1billion

Exxon - $35.3billion

Procter & Gamble - $34.3billion

AmericanExpress - $32.8billion

Motorola - $31.3billion

NEC - $30.3billion

Mitsubishi Electric - $29.8billion

Nippon Telegraph andTelephone - $28.7billion

Hewlett-Packard - $28.5billion

Citicorp - $28.4billion

Unilever - $27.4billion

Honda Motor - $26.9billion

Time Warner - $26.1billion

Nestle - $26.1billion

BASF - $25.8billion

Hitachi - $25.7billion

Novartis - $25.6billion

InternationalPaper - $25.2billion

Mitsui & Co. - $24.7billion

Sony - $24.6billion

Matsushita Electric - $24.4billion

ICI - $24.4billion

Dow Chemical - $23.8billion

Boeing - $23.6billion

Tokyo ElectricPower - $23.2billion

Texaco - $22.6billion

RobertBosch - $22.5billion

Deutsche Bank - $22.4billion

Dow Jones - $22.4billion

Chase Manhattan - $22.4billion

Ericsson - $22.3billion

Total - $22.2billion

Samsung Electronics - $22.2billion

AmericanInternationalGroup - $22.1billion

Sanwa Bank - $22.1billion

 

ただインターネット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

Permalink |記事への反応(0) | 20:58

このエントリーをはてなブックマークに追加ツイートシェア

2023-02-22

tiktokだがyoutubeショートやらで唯一ぐっときたやつ

わたし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

それは無意味スクロールしてほとんど記憶に残らず無駄時間消費してしまうのです

その時間もっとなにか勉強経験に、とは言わないがすごく虚無な時間が気がする

この感情に関しては私自身うまく説明できないし

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

何度かこの経験をしてからTiktokなどは見ないようにしていた

しかし、半年から広告代理店で働くようになり、Webマーケティング部門配属でTiktokなどは無視できないようになってしまった。

その中でリサーチとして見るようになって見つけたもの

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.

私は、不可能を可能にする方法を考え出しました。

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.

10年前、これは現実からほど遠いものでした。

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.

しかしたら、私たち生理現象横取りして、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.

から、こんなことは不可能なのかもしれない。

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.

でも、最悪なのは、それを止める方法がわからないことです。

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

Permalink |記事への反応(0) | 23:03

このエントリーをはてなブックマークに追加ツイートシェア

2023-01-22

GPT医療現場で使われる可能性について聞いてみた

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GPTが使われるようになる可能性を聞いてみた。

GPT-3の実装を軽く確認

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使用して学習されました。これは大量のテキストデータ学習し、自然言語処理タスク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使用して、テキストを処理します。それは、大量のデータ効率的に処理するために、Attention機構使用します。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、自然言語翻訳文章解釈質問応答などのタスク適用されており、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使用して、言語モデル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使用することで、新しいタスクに対して学習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、大量のデータ使用して学習し、高い精度を達成するために必要パラメータ数です。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技術進歩によって、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使用することで、新しいタスクに対して学習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GTP-2、現バージョンGPT-3、次バージョン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使用して学習し、自然言語処理タスク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、大量のデータ使用して学習し、高い精度を達成するために必要パラメータ数です。これは、現在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英語表現して。

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使用することで、新しいタスクに対して学習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知識学習します。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、単語文章関係性、文章構造文章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機構使用して、大量のテキストデータから概念レベル知識学習し、文章意味理解することができるようになります

Permalink |記事への反応(1) | 00:13

このエントリーをはてなブックマークに追加ツイートシェア

2023-01-19

ChatGPTにお前はどうやって実装されてんの?って聞いてみたら

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?

ChatGPT:

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.

ChatGPT:

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?

ChatGPT:

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:

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?

ChatGPT:

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?

ChatGPT:

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:

Thankyou.By the way, whatis myname?

ChatGPT:

You've mentionedyournameis Masuda.

Permalink |記事への反応(4) | 13:38

このエントリーをはてなブックマークに追加ツイートシェア

2022-11-02

anond:20221102125622

「4000億の星の群れ」(Four HundredBillionStars

 

なお中身は普通

Permalink |記事への反応(0) | 17:57

このエントリーをはてなブックマークに追加ツイートシェア

2022-03-16

anond:20220316222605

なんでラディッシュなのかと思ってたら、一口で楽しめる→気軽にたのしめるライトノベル的なロマンス小説サイトってことか。

というか、ロマンス小説サイトなのか…通りでログイン直後に聞かれた「好きなジャンルは?」が「billion〜(億万長者のはなし)」「禁断〜」とかのわけだ…。

Permalink |記事への反応(0) | 23:06

このエントリーをはてなブックマークに追加ツイートシェア

2021-11-19

世界メディアミックスランキングって正しい?

タイトルの記事2019年で少し古いけど、日本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wikipediaList of highest-grossing media franchises

wiki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)

2002–2009 – $29.688billion

$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から日本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。

そもそも世界の売上を比較するランキング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。

どっかの本でもこのデータ引用されてるらしいけど、ちゃん検証してほしいわ。

Permalink |記事への反応(0) | 09:51

このエントリーをはてなブックマークに追加ツイートシェア

2021-07-15

anond:20210715001433

7Billion Humans

Permalink |記事への反応(0) | 13:34

このエントリーをはてなブックマークに追加ツイートシェア

2021-07-13

anond:20210713100729

東南アジアでひっそりやってるだけやろ。

スポーツ人気順で言えばこう。

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

9. AmericanFootball / Rugby - 410 Million Followers

10.Golf - 390 Million Followers

Permalink |記事への反応(2) | 10:12

このエントリーをはてなブックマークに追加ツイートシェア

2021-02-14

anond:20210214123603

なんか伝わってなかったみたいだから表にする。

数字 従来手法日本語 従来手法英語提案手法
1one
10 ten
10^2 hundred
10^3 thousand 十百
10^4 ten thousand
10^5 十万 hundred thousand 十千
10^6 百万 million 百千
10^7千万 ten million 十百千
10^8 hundred million
10^9 十億billion 十万
10^10 百億 tenbillion 百万
10^11 千億 hundredbillion 十百万
10^12trillion千万
10^13 十兆 tentrillion千万
10^14 百兆 hundredtrillion千万
10^15 千兆 十百千万
10^16
10^17 十京 十億
10^18 百京 百億
10^19 千京 十百億
10^20 千億
10^21 十千億
10^22 百千億
10^23 十百千億
10^24 万億
10^25 十万億

覚える記号の数が少なくてもロジカルに巨大な数値が表現できる。

Permalink |記事への反応(0) | 18:20

このエントリーをはてなブックマークに追加ツイートシェア

anond:20210214123603

million,billion,trillion...がそれや

Permalink |記事への反応(0) | 12:50

このエントリーをはてなブックマークに追加ツイートシェア

2020-06-15

どのゲームをすればよいのか

死ぬほどSteam積みゲーが増えてきたので次にやるべきゲームを教えて欲しい。

やらずに死ねるか?ってゲーム、この中にあるかな

プレイしたものは下にプレイ時間が書いてあるので参考にして欲しい。

Sid Meier'sCivilization V

記録時間: 977時間

Fallout 4

記録時間: 366時間

TheLast Remnant

記録時間: 194時間

The Elder Scrolls V: Skyrim Special Edition

記録時間: 191時間

Sid Meier'sCivilizationVI

記録時間: 191時間

Terraria

記録時間: 189時間

サガ スカーレット グレイス緋色の野望

記録時間: 133時間

The Elder Scrolls V: Skyrim

記録時間:92時間

Stardew Valley

記録時間: 81時間

Human: FallFlat

記録時間: 71時間

NieR:Automata

記録時間: 57時間

Romancing SaGa 3

記録時間: 38時間

Bayonetta

記録時間: 21時間

Gorogoa

記録時間: 14.1時間

KatanaZERO

記録時間:11.8時間

ショベルナイト

記録時間:10.8時間

Age of Empires II (2013)

記録時間:9.6時間

超次次元ゲイム ネプテューヌRe;Birth1

記録時間: 6.8時間

Portal

記録時間: 6.6時間

ThisWar ofMine

記録時間: 5.7時間

KIDS

記録時間: 4.6時間

The Herbalist

記録時間: 4.4時間

Overcooked

記録時間: 4.1時間

BabaIsYou

記録時間: 3.9時間

A-TrainPC Classic / みんなのA列車で行こうPC

記録時間: 2.9時間

AntVentor

記録時間: 2.8時間

Helltaker

記録時間: 2.3時間

INVERSUS Deluxe

記録時間: 2.3時間

Portal 2

記録時間: 1.9時間

Botanicula (ボタニキュラ)

記録時間: 1.8時間

DonutCounty

記録時間: 1.7時間

ARCADE GAME SERIES: DIG DUG

記録時間: 1.6時間

UNDER NIGHT IN-BIRTHExe:Late

記録時間: 1.6時間

ARCADE GAME SERIES:PAC-MAN

記録時間: 1.5時間

Human ResourceMachine

記録時間: 1.3時間

Everything

記録時間: 1.2時間

Move or Die

記録時間: 1.0時間

FluidLander

記録時間: 0.9時間

Arcade ClassicsAnniversary Collection

記録時間: 0.9時間

Half-Life

記録時間: 0.8時間

Counter-Strike: Global Offensive

記録時間: 0.8時間

Tricky Towers

記録時間: 0.8時間

NOBUNAGA’S AMBITION: Zenkokuban

記録時間: 0.6時間

Hotline Miami

記録時間: 0.6時間

NOBUNAGA’S AMBITION: Sengoku Gunyuuden

記録時間: 0.6時間

Half-Life 2

記録時間: 0.6時間

StickFight:The Game

記録時間: 0.5時間

Warframe

記録時間: 0.5時間

ARCADE GAME SERIES: GALAGA

記録時間: 0.4時間

Fallout

記録時間: 0.3時間

Street Fighter 30thAnniversary Collection

記録時間: 0.3時間

NOBUNAGA’S AMBITION: Reppuden withPower Up Kit

記録時間: 0.3時間

NOBUNAGA’S AMBITION: Shouseiroku withPower Up Kit

記録時間: 0.3時間

Ace of Seafood

記録時間: 0.3時間

NOBUNAGA'S AMBITION: Bushou Fuunroku

記録時間: 0.3時間

Fallout 3 - Game of the Year Edition

記録時間: 0.2時間

The Elder Scrolls IV: Oblivion

記録時間: 0.2時間

プラグ・アンド・プレイ

記録時間: 0.2時間

LittleInferno

記録時間: 0.2時間

MrShifty

記録時間: 0.2時間

STAR WARS Battlefront (Classic, 2004)

記録時間: 0.1時間

Duck Game

記録時間: 0.1時間

PuyoPuyo Champions -ぷよぷよeスポーツ

記録時間: 0.1時間

NOBUNAGA'S AMBITION

記録時間: 0.1時間

UNDEFEATED

記録時間: 0.1時間

RocketLeague

記録時間: 0.1時間

Ultimate Chicken Horse

Mushihimesama

NOBUNAGA’S AMBITION: Haouden withPower Up Kit

Sid Meier'sCivilizationIV:Beyond the Sword

Stronghold CrusaderHD

Groove Coaster

Counter-Strike

8-BitBayonetta

Hacknet

Undertale

Niffelheim

SkyrimScript Extender (SKSE)

Counter-Strike: Source

Ricochet

Team Fortress Classic

Deathmatch Classic

KHOLAT

Sid Meier'sCivilizationIV: Colonization

STEINS;GATE

Day of Defeat: Source

Sid Meier'sCivilizationIV

Unepic

TIS-100

NEKOPARA Vol. 1

DARK SOULS III

超次次元ゲイム ネプテューヌRe;Birth2

FINAL FANTASY X/X-2HD Remaster

7BillionHumans

428 〜封鎖された渋谷で〜

Age of Empires II (2013): The Forgotten

Aoki Ookami to Shiroki Mejika

Atelier Meruru ~TheApprentice of Arland~ DX

Atelier Rorona ~TheAlchemist of Arland~ DX

Atelier Totori ~The Adventurer of Arland~ DX

Autonauts

BADLAND: Game of the Year Edition

BanditKings of AncientChina

Batman: ArkhamKnight

Battlestations:Midway

Battlestations:Pacific

Borderlands 2

Borderlands 2: Headhunter 1:BloodyHarvest

Borderlands 2: Headhunter 2: WattleGobbler

Borderlands 2: Headhunter 3: Mercenary Day

Borderlands 2: Headhunter 4:Wedding Day Massacre

Borderlands 2: Headhunter 5: Son of Crawmerax

Borderlands: The Pre-Sequel

BorderlandsDLC: Claptrap’s NewRobotRevolution

BorderlandsDLC:Mad Moxxi's UnderdomeRiot

BorderlandsDLC: TheSecret Armory of General Knoxx

BorderlandsDLC: The ZombieIsland of Dr. Ned

BorderlandsGOTY

BorderlandsGOTY Enhanced

Cat Quest

Cat Quest II

Celeste

CHUCHEL (チュチェル)

Circle Empires

Civilization V - Scrambled ContinentsMap Pack

CivilizationVI -AustraliaCivilization & Scenario Pack

CivilizationVI - AztecCivilization Pack

CivilizationVI - Persia and MacedonCivilization & Scenario Pack

CivilizationVI -PolandCivilization & Scenario Pack

CivilizationVI -Vikings Scenario Pack

Conflict: DeniedOps

Counter-Strike: ConditionZero

Counter-Strike: ConditionZero Deleted Scenes

Cuphead

Day of Defeat

Deathtrap

Depraved

Deus Ex: Game of the Year Edition

Deus Ex:HumanRevolution -Director's Cut

Deus Ex: InvisibleWar

Deus Ex: Mankind Divided

Deus Ex:The Fall

Dungeon Siege

Dungeon Siege 2

Dungeon Siege III

EverythingOST

Fallout 2

Fallout 4 - Contraptions Workshop

Fallout: New Vegas

FalloutTactics

FINAL FANTASY TYPE-0HD

FINAL FANTASY XII THEZODIACAGE

Flora's Fruit Farm

Forager

Genghis Khan

Genghis Khan II: Clan of the GrayWolf

Goetia

Grand Theft Auto V

Hacknet -Labyrinths

Half-Life 2:Deathmatch

Half-Life 2: EpisodeOne

Half-Life 2: EpisodeTwo

Half-Life 2:Lost Coast

Half-Life:BlueShift

Half-Life: Opposing Force

Half-Life: Source

Half-LifeDeathmatch: Source

Hearts of IronIV

Hearts of IronIV:Death or Dishonor

Hearts of IronIV:Together forVictory

Hellsinker.

HitmanGO: Definitive Edition

I Love You, Colonel Sanders! A Finger Lickin’Good Dating Simulator

Ishin noArashi

Just Cause

Just Cause 2

Just Cause 3

Just Cause 3DLC:SkyFortress Pack

Kane & Lynch 2:Dog Days

Kane & Lynch: Dead Men

Kawanakajima no Kassen /川中島の合戦

Kenshi

KILLla KILL -IF

Lara Croft and the Guardian ofLight

Lara Croft and the Temple of Osiris

Lara CroftGO

Left 4 Dead

Left 4 Dead 2

Legacy of Kain: Defiance

Legacy of Kain:Soul Reaver

Legacy of Kain:Soul Reaver 2

Life Goes On

Lifeis Strange

Lode RunnerLegacy

Mark of theNinja: Remastered

Meltys Quest

Mindustry

MiniNinjas

MushihimesamaOriginalSoundtrack

Mushihimesama V1.5

NEKOPARA Vol. 0

NEKOPARA Vol. 2

NEKOPARA Vol. 3

NieR:Automata - 3C3C1D119440927

NOBUNAGA’S AMBITION: Ranseiki withPower Up Kit

NOBUNAGA’S AMBITION: Soutenroku withPower Up Kit

NOBUNAGA’S AMBITION: Tenkasousei withPower Up Kit

OCTOPATH TRAVELER

Order ofWar

Overcooked! 2

PAYDAY 2

PCBuilding Simulator

Pikuniku

PolyBridge

Prelogate

Project: Snowblind

PuyoPuyoTetris®

Red Dead Redemption 2

Rise of theTomb Raider

Romance of the Three Kingdoms

Romance of the Three Kingdoms II

Romance of the Three Kingdoms III

Romance of the Three KingdomsIV withPower Up Kit

Romance of the Three KingdomsIX withPower Up Kit

Romance of the Three KingdomsVIII withPower Up Kit

Romance of the Three KingdomsVII withPower Up Kit

Romance of the Three KingdomsVI withPower Up Kit

Romance of the Three Kingdoms V withPower Up Kit

Romance of the Three Kingdoms X withPower Up Kit

RussianSubway Dogs

Sangokushi Eiketsuden

Seed of the Dead

Sekiro:Shadows Die Twice

ShadowTactics: Blades of theShogun

Sid Meier'sCivilizationIV

Sid Meier'sCivilizationIV:Beyond the Sword

Sid Meier'sCivilizationIV: Colonization

Sid Meier'sCivilizationIV:Warlords

Sid Meier'sCivilizationIV:Warlords

Sid Meier'sCivilization V:Brave New World

Sid Meier’sCivilizationVI:Rise and Fall

Skyrim HighResolution Texture Pack

Sleeping Dogs: Definitive Edition

SNK 40thAnniversary Collection

SpaceChem

STEINS;GATE 0

STEINS;GATE ELITE

STEINS;GATE 線形拘束のフェノグラム

Stronghold CrusaderExtremeHD

StrongholdHD

StrongholdLegends

Super Lucky's Tale

Supreme Commander 2

Swag and Sorcery

Taikou Risshiden

Team Fortress 2Beta

Thefriends of RingoIshikawa

The Incredible Adventures ofVan Helsing

The Incredible Adventures ofVan Helsing: Thaumaturge

The Incredible Adventures ofVan Helsing II

The Incredible Adventures ofVan Helsing II -OST

The Incredible Adventures ofVan Helsing III

The Messenger

The Tiny BangStory

The TuringTest

The Witcher 2: Assassins ofKings Enhanced Edition

The Witcher 3: Wild Hunt

The Witcher 3: Wild Hunt - Expansion Pass

The Witcher 3: Wild Hunt - New Finisher Animations

The Witcher: Enhanced Edition

Thief

Thief -Ghost

Thief - Opportunist

Thief -Predator

Thief - The Bank Heist

Thief 2

Thief: DeadlyShadows

ThiefGold

ThisWar ofMine -War Child CharityDLC

Tomb Raider

Tomb Raider (VI): TheAngel ofDarkness

Tomb Raider:Anniversary

Tomb Raider: Chronicles

Tomb Raider:Legend

Tomb Raider: TheLast Revelation

Tomb Raider:Underworld

Tomb Raider I

Tomb Raider II

Tomb Raider III: Adventures ofLara Croft

UnchartedWaters

UnchartedWaters II

VA-11 Hall-A: Cyberpunk BartenderAction

Van Helsing II:Ink Hunt

Winning Post

World ofGoo

XCOM 2

XCOM 2:Alien Hunters

XCOM 2: Anarchy's Children

XCOM 2: Reinforcement Pack

XCOM 2:ResistanceWarrior Pack

XCOM 2:Shen'sLastGift

XCOM 2:War of the Chosen

XCOM: Enemy Unknown

XCOM: Enemy Within

ZeroEscape: The Nonary Games

ZeroEscape:ZeroTime Dilemma

三國志11 withパワーアップキット

三國志12 withパワーアップキット

大神絶景

神次次元ゲイム ネプテューヌRe;Birth3 V CENTURY

次元大戦ネプテューヌVSセガハードガールズ夢の合体スペシャル

超次次元ゲイム ネプテューヌRe;Birth1 DELUXEセット(ディジタル限定版)

超次次元ゲイネプテューヌRe;Birth3デラックスセット

[お礼]

みんな、ご意見ありがとう

みんな言うことバラバラ面白い

返信:

・ラスレムについて

初めてのSteamゲームパッケージ買ったのにSteamインストールさせ沼。

プレイ時間が長いのはクエストを全てこなしたからかな。乱殺までしてないです。

リマスターは出るんですかね。

マイクラ

エンダードラゴン倒すまではやった。

デトロイト

PS4プレイ済み。面白いけど、QTE邪魔。もう一周するとき難易度を下げる。

Portal2

酔った。1は大丈夫だったのになぁ。

・物量

セールときに買ってたらこんな事になった。金持ちなわけでは。むしろ安物買いの銭失い。

KOEI系も周年記念で安売りしてたから。

Permalink |記事への反応(13) | 23:01

このエントリーをはてなブックマークに追加ツイートシェア

次の25件>
ログインユーザー登録
ようこそ ゲスト さん
Copyright (C) 2001-2025 hatena. All Rights Reserved.

[8]ページ先頭

©2009-2025 Movatter.jp