はてなキーワード: DATEとは
https://b.hatena.ne.jp/site/anond.hatelabo.jp
で動くスクリプトでたとえば投稿後10分以内にブクマされページに乗ったら「1 user」が「1 user セルクマ 1とか5(何分後にブクマされたか)」になる。もしマイナスなら誤判定なので無視して。
時間を置いたセルクマには効かないし普通のファーストブクマカがどれぐらいの頻度で確認してるかしらないけど5分以内や1分以内もポロポロあるのでまあ目安に。
.forEach(div => {
('.entrylist-contents-title > a')
とかの
を
<>
に変えてね
他にも見落としあるかも
誤判定が減るから非公開ファーストブクマを判定できたらいいんだけどね。
// ==UserScript== // @name hatebu masuda selkmark // @namespace http://tampermonkey.net/ // @version 0.1 // @description 特定時間以内にブクマされた増田を強調する // @author You // @match https://b.hatena.ne.jp/site/anond.hatelabo.jp* // @grant none // ==/UserScript== (function() { 'use strict'; const threshold = 60 * 10 // 何秒以内か const domain = 'https://anond.hatelabo.jp/' const dateTemplate = '202301020304' // 時分まで urlの時刻表記 const dateTest = new RegExp('\\d{' + dateTemplate.length + '}') document.querySelectorAll('div.entrylist-contents').forEach(div => { const masuda = div.querySelector('.entrylist-contents-title > a') const dateStr = masuda.href.substring(domain.length + dateTemplate.length, domain.length) if (!dateTest.test(dateStr)) { // キーワードとか console.log('not diary', dateStr) return } // new Dateできるように変換 // https://amateur-engineer.com/javascript-date-yyyymmddhhmm/ const year = parseInt(dateStr.substring(0, 4)) const month = parseInt(dateStr.substring(4, 6)) const day = parseInt(dateStr.substring(6, 8)) const hour = parseInt(dateStr.substring(8, 10)) const min = parseInt(dateStr.substring(10, 12)) const date = new Date(year, month - 1, day, hour, min) const bukumaDate = new Date(div.querySelector('.entrylist-contents-date').textContent) // 2023/01/23 00:00 const diffSec = (bukumaDate - date) / 1000 // ms to sec if (diffSec > threshold) { return } // ブクマ数 user const user = div.querySelector('span.entrylist-contents-users a').lastChild user.textContent += ' セルクマ ' + (diffSec / 60) // 古い記事がマイナスになる でも2015年ぐらいの記事までかな?新着はセーフ臭い /* if(diffSec < 0) { user.textContent += ' 異常差分:' + diffSec } */ }) })();
date raider ww
スパムメールに騙されて、スパム文面(下記参照)の「振込入金の詳細については、SMBCダイレクトでご確認いただけます。」のURLリンクを踏んでしまいました。
だけど、それは謂わばスパム側による囮の様なURLで、三井住友銀行のドメインだったので、幸運にも今回は難を逃れることができました。
今回のスパム側の主な目的は、メール受診者(スパム被害者)がHTML形式でメールを確認して、また、メールの内容を信頼して「ご確認」のURLリンク「ttps://www.shuhmsドットcom」(詐欺サイト)をクリックすることだと思われます。
私は普段から平文形式でメールを確認するので、(実際の被害を受けるという意味では)今回難を逃れたけど、普段からHTML形式でメールを確認していたり、情報弱者や高齢者だったら騙されやすいだろうと感じます。
ポイントは、「ご確認」のリンク先が「ttps://www.shuhmsドットcom」になっていた他、「振込入金の詳細については、SMBCダイレクトでご確認いただけます。」の次の行のURLの/kojin以下の文字列がオリジナルと違うことです。
それ以外、題名、送信元、メール内容についてオリジナルに擬態しています。
普段からスパムメールに注意していますが、スパムの擬態が高度化して、情報弱者が騙されやするなる閾値を超えたと感じたので、警鐘の意味を込めて書いておきます。
【スパムメール】
-------------------------------------------------------------------------
Subject: 【三井住友銀行】振込入金失敗のお知らせ
Date: Thu, 9 Mar 2023 **:**:** +0800
From: 三井住友銀行 <SMBC_service@dn.smbc.co.jp>
-------------------------------------------------------------------------
-------------------------------------------------------------------------
Date: Sat, 25 Feb 2023 **:**:** +0900
From: 三井住友銀行 <SMBC_service@dn.smbc.co.jp>
Reply-To: SMBC.Auto.reply@ar.smbc.co.jp
-------------------------------------------------------------------------
-------------------------------------------------------------------------
三井住友銀行より、ご指定口座への振込入金失敗についてお知らせします。
振込入金の詳細については、SMBCダイレクトでご確認いただけます。
ttps://www.smbc.co.jp/kojin/app/smbcapp.html?aff=dirct_mlODM1902001(←kojin以下の文字列がオリジナルと違う)
―――――――――――――――――――――
※振込依頼人から振込の「取消」「変更」「組戻」があった場合等、お知らせした明細と実際の手続が異なる場合があ
ります。
※本メールは、お客さまお届けのメールアドレスへお送りしています(本メールの再送依頼は受け付けておりません)
。
偽のメール等で誘導された当行を装う偽サイトに、お客さまの口座情報やワンタイムパスワード等を入力すると、不正
> ttps://www.smbc.co.jp/kojin/special/stop_phishing_crime/
「三井住友銀行」名でお送りするメールには、携帯キャリアのメールアドレス宛を除き全て電子署名を付けています。
> ttps://www.smbc.co.jp/security/smime/
閲覧しているサイトが当行の正当なサイトかどうかを、電子証明書により確認いただけます。
> ttps://qa.smbc.co.jp/faq/show/297?site_domain=default
本メールに対するメールでのご返信・お問い合わせはお受けしておりません。メールの内容に身に覚えがない場合や、
サービス等についてくわしく知りたい場合は、当行ホームページをご覧いただくか、以下より電話番号を確認の上、お
問い合わせください。
> ttps://www.smbc.co.jp/contact_list.html
> ttps://direct.smbc.co.jp/aib/aibgsjsw5001.jsp?sc=081
-----------------------------------------------------------------------
-------------------------------------------------------------------------
ChatGPTさんも、そんな考えは時代遅れやって言うてはるぞ。
Sure, I'd be happy to discuss that with you! The question of who should pay on a first date is a common one and there's no one-size-fits-all answer. It really depends on the situation and the preferences of the people involved.
Traditionally, it was often expected that the man would pay for the first date. However, in modern times, many people prefer to split the bill or take turns paying for dates. Some people may feel strongly about paying on a first date as a way to show their interest or to demonstrate their ability to provide for their partner, while others may feel that splitting the bill or taking turns paying is more fair and equitable.
Ultimately, the decision of who should pay on a first date should be based on what both people are comfortable with. It's a good idea to discuss it ahead of time so that there are no surprises or awkward moments at the end of the date. Communication is key in any relationship, so it's important to be open and honest about your preferences and expectations.
ChatGPT:
Yes, I can provide confidence scores with my answers when they might be inaccurate. However, please note that the confidence score is based on the model's understanding of the input and context and is not a measure of the accuracy of the answer.
ふむふむ・・・・(中略)
つけてくれへんやんけ
ワイ:
ChatGPT:
I apologize, as a language model, I don't have the capability to calculate confidence scores for individual sentences. However, I have been trained on a large dataset, and I will do my best to provide accurate information based on my knowledge cut-off.
Please note that the information provided might not be up-to-date and it's always good to double-check the information with the official source.
そこも嘘かーい
ワイ:
You said "Yes, I can provide confidence scores with my answers when they might be inaccurate. ".
ChatGPT:
I apologize for the confusion, as a language model, I do not have the capability to assign confidence scores to my responses. I apologize for any confusion caused by my previous response. My main goal is to provide the most accurate information based on my training data, however, the information provided may not be up-to-date or may contain inaccuracies.
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:
下記はカリフォルニア大学のビアンカ・アセベド博士の研究紹介動画と書籍と記事(Pod cast)、
興味があればどうぞ
HSP brain studies
https://www.youtube.com/watch?v=qep36Vy_0pE
> Did you know that the brain of a highly sensitive person (HSP) works differently?
> The results of fMRI brain studies conducted by Dr. Elaine Aron, Dr. Art Aron, Dr. Bianca Acevedo and their colleagues are quite fascinating.
エレイン・アロン博士、アート・アロン博士、ビアンカ・アセベド博士らが行ったfMRIによる脳の研究結果は、かなり魅力的です。
[Amazon] The Highly Sensitive Brain: Research, Assessment, and Treatment of Sensory Processing Sensitivity 1st Edition
https://www.amazon.com/Highly-Sensitive-Brain-Assessment-Sensitivity/dp/0128182512
> The Highly Sensitive Brain is the first handbook to cover the science, measurement, and clinical discussion of sensory processing sensitivity (SPS),
> a trait associated with enhanced responsivity, awareness, depth-of-processing and attunement to the environment and other individuals.
> Grounded in theoretical models of high sensitivity, this volume discusses the assessment of SPS in children and adults,
> as well as its health and social outcomes.
> This edition also synthesizes up-to-date research on the biological mechanisms associated with high sensitivity,
> such as its neural and genetic basis. It also discusses clinical issues related to SPS and seemingly-related disorders such as misophonia,
> a hyper-sensitivity to specific sounds. In addition, to practical assessment of SPS embedded throughout this volume is discussion of the biological basis of SPS,
> exploring why this trait exists and persists in humans and other species.
>
>The Highly Sensitive Brain is a useful handbook and may be of special interest to clinicians, physicians, health-care workers, educators, and researchers.
『高感度脳』は、感覚処理感度(SPS)の科学、測定、臨床的考察を網羅した初めてのハンドブックです。この巻では、高感度の理論モデルに基づいて、子どもと成人のSPSの評価、健康と社会的転帰について論じています。また、高感受性の神経基盤や遺伝的基盤など、高感受性に関連する生物学的メカニズムに関する最新の研究をまとめています。また、SPSの臨床的な問題点や、特定の音に過敏に反応するミソフォニアなど、一見関連していると思われる疾患についても解説しています。さらに、この巻全体に組み込まれたSPSの実用的な評価に加えて、SPSの生物学的基盤についての議論があり、なぜこの形質がヒトや他の種に存在し、持続するのかを探っています。
臨床医、医師、医療従事者、教育者、研究者にとって有益なハンドブックです。
[foreverbreak] Highly Sensitive People How to Tell If You’re an HSP + Shedding Light on This Misunderstood Trait
非常に敏感な人々 あなたがHSPであるかどうかを見分ける方法+この誤解されている特性に光を当てる
https://foreverbreak.com/podcast/s1/e5/
まぁ、アセベト博士でなくてもいいけど(TEDとかにもあるよ)
ってなってるね
下記はカリフォルニア大学のビアンカ・アセベド博士の研究紹介動画と書籍と記事(Pod cast)、
興味があればどうぞ
HSP brain studies
https://www.youtube.com/watch?v=qep36Vy_0pE
> Did you know that the brain of a highly sensitive person (HSP) works differently?
> The results of fMRI brain studies conducted by Dr. Elaine Aron, Dr. Art Aron, Dr. Bianca Acevedo and their colleagues are quite fascinating.
エレイン・アロン博士、アート・アロン博士、ビアンカ・アセベド博士らが行ったfMRIによる脳の研究結果は、かなり魅力的です。
[Amazon] The Highly Sensitive Brain: Research, Assessment, and Treatment of Sensory Processing Sensitivity 1st Edition
https://www.amazon.com/Highly-Sensitive-Brain-Assessment-Sensitivity/dp/0128182512
> The Highly Sensitive Brain is the first handbook to cover the science, measurement, and clinical discussion of sensory processing sensitivity (SPS),
> a trait associated with enhanced responsivity, awareness, depth-of-processing and attunement to the environment and other individuals.
> Grounded in theoretical models of high sensitivity, this volume discusses the assessment of SPS in children and adults,
> as well as its health and social outcomes.
> This edition also synthesizes up-to-date research on the biological mechanisms associated with high sensitivity,
> such as its neural and genetic basis. It also discusses clinical issues related to SPS and seemingly-related disorders such as misophonia,
> a hyper-sensitivity to specific sounds. In addition, to practical assessment of SPS embedded throughout this volume is discussion of the biological basis of SPS,
> exploring why this trait exists and persists in humans and other species.
>
>The Highly Sensitive Brain is a useful handbook and may be of special interest to clinicians, physicians, health-care workers, educators, and researchers.
『高感度脳』は、感覚処理感度(SPS)の科学、測定、臨床的考察を網羅した初めてのハンドブックです。この巻では、高感度の理論モデルに基づいて、子どもと成人のSPSの評価、健康と社会的転帰について論じています。また、高感受性の神経基盤や遺伝的基盤など、高感受性に関連する生物学的メカニズムに関する最新の研究をまとめています。また、SPSの臨床的な問題点や、特定の音に過敏に反応するミソフォニアなど、一見関連していると思われる疾患についても解説しています。さらに、この巻全体に組み込まれたSPSの実用的な評価に加えて、SPSの生物学的基盤についての議論があり、なぜこの形質がヒトや他の種に存在し、持続するのかを探っています。
臨床医、医師、医療従事者、教育者、研究者にとって有益なハンドブックです。
[foreverbreak] Highly Sensitive People How to Tell If You’re an HSP + Shedding Light on This Misunderstood Trait
非常に敏感な人々 あなたがHSPであるかどうかを見分ける方法+この誤解されている特性に光を当てる
https://foreverbreak.com/podcast/s1/e5/
名著「UNIXという考え方 - UNIX哲学」は本当に名著なのか? 〜 著者のガンカーズは何者なのかとことん調べてみた - Qiita
この記事はよく調べてあるなぁと思う反面,事実関係の間違いも多く当時の空気感など欠けていると思う部分がいくつかある。事実関係に関しては追い切れないので参考文献を挙げるにとどめておくが,空気感のほうはいくつか書いておく。なお当該記事の「当時と今では状況が全然違うんだから,安易に『UNIX 哲学』とかいうな」という主旨には大賛成である。
初期の UNIX の歴史について興味がある向きには次の書籍をお薦めする。
Peter H. Salus『A Quarter Century of UNIX』(1994, Addison-Wesley Publishing)
和訳の『UNIXの1/4世紀』(Peter H. Salus, QUIPU LLC 訳, 2000, アスキー) は絶版のうえ訳も微妙なので薦めづらいが,原書は The Unix Heritage Society (tuhs) で PDF が無償公開されているので,英語が苦にならないのなら読んでみるといい。
また同じく tuhs で無償公開されている Don Libes and Sandy Ressler『Life with UNIX』(1989, Prentice Hall)を読めば80年代終りの UNIX の状況(XENIX についてもしっかり言及されている)や利用者目線での雰囲気もある程度判るだろう。
元記事で一番気になるのが「哲学」という語の捉え方。この言葉の強さに引きずられているように読める。でもこれ,当時は設計の基本的な考え方くらいの意味でわりとよく使われていた言葉なんだよね。たとえば米 BYTE 誌のアーカイブを “philosophy” で全文検索するとこんな感じ。
https://archive.org/details/byte-magazine?query=philosophy&sin=TXT&sort=date
ほぼ毎号のように出現していたのが判るだろう。
もっとも猫も杓子も「哲学」を振りかざしていたわけではないし,UNIX の開発者たちが「哲学」の語を好んで使っていたのも間違いないように思う。傍証の一つが AT&T の定期刊行物『The Bell System Technical Journal』の1978年7, 8月号だ。元記事で言及されているマキルロイの Forword の初出がこれで,ネットのアーカイブから PDF が入手できる。
この号は二部構成になっていて第一部が Atlanta Fiber System に関する論文12本(全172ページ),第二部が UNIX に関する(Preface や Foreword を含む)論文22本(全416ページ)となっている。さて前述の PDF は OCR されているので “philosophy” で全文検索してみると8箇所見つかる。これが見事に全部 UNIX の論文なのだ。もちろん論文の性質もページ数も違うからこれだけで確定的なことはいえないが「日常的に使っていたんだろうなぁ」という推測は成り立つだろう。じつはマキルロイの哲学とされている部分は “Style” であり “philosophy” の語は一切使われていないというのもちょっと面白い。UNIX の開発者たちがなぜ「哲学」という語を好んだか正確なところは判らないが,それまでにない新しい考え方に基づいた OS を開発しているという意識があれば,そういう言葉を選ぶのが自然な時代だったことは間違いない。
UNIX が認知され拡がっていく過程で「哲学」も知られるようになっていった。自分が好むものの良さを他人にも識ってもらいたい,あわよくば他人もそれを好むようになって欲しいという布教活動は今も昔を変らないわけで「哲学」はその便利なツールとなったわけだ。元記事ではガンカースの著作を「外部の人間が後から打ち立てた哲学」と表現しているが,そんなたいしたものではない。マキルロイの論文に影響を受けた布教のためのああいう説教は到るところにあった。たとえば前掲の『Life with UNIX』にもしっかり Philosophy の項がある。また日本で最初期の UNIX 解説本のひとつである,村井純・井上尚司・砂原秀樹『プロフェッショナル UNIX』(1986,アスキー)には冒頭次のような一節がある。
オペレーティング・システムは,コンピュータを使うものにとっての環境を形成する基盤であるから,そのうえで生活する者の個性を尊重し,より良い環境へと作り上げて行く課程を支援するような素材を提供するソフトウェアでなければならない。この主張こそが,UNIX のオペレーティング・システムとしての個性ではないだろうか。
「より良い環境へと作り上げて行く課程を支援するような素材を提供するソフトウェア」とはテキストを入出力フォーマットとする単機能のコマンド群のことで,これらをパイプでつなげたりシェルスクリプトでまとめたりすることで「そのうえで生活する者の個性を尊重し」た「より良い環境へと作り上げて行く」ということだ。こういった説教はありふれたものであった。たんにそれを「哲学」の語を用いて書籍にまとめたのが,たまたまガンカースだったというだけのことである。
そしてじつは UNIX の場合,布教活動とはべつに「哲学」を広めなければならない切実な理由があった。これを説明するのは非常に面倒くさい。当時と今ではあまりにも環境が違うのだが,その違いが判らないと切実さが伝わらないからだ。マア頑張ってみよう。
UNIX は PDP というミニコンピュータ(ミニコン)上に開発された。このミニコンを使うためには専用の部屋に行く必要がある。その部屋は,もちろん場所によって違うわけだが,マアおおよそ学校の教室くらいの大きさだ。長机が何列か並んでおり,そのうえにはブラウン管ディスプレイとキーボードを備えた機器が等間隔に置かれている。壁際にはプリンタが何台かあるだろう。通っていた学校にコンピュータ室などと呼ばれる部屋があったならそれを思い浮かべればだいたい合ってる。ただし置かれている機器はコンピュータではなくコンピュータに接続するための端末装置(ターミナル)だ。端末装置のキーボードで打った文字がコンピュータに送られコンピュータが表示した文字がそのディスプレイに表示される。現在 Unix 系 OS で CLI を使うときターミナルとか xterm という名のアプリケーションを用いるがこれらは端末装置のエミュレータで,もともとは実体のある装置だったわけだ。
さてコンピュータ室にたいていは隣接するかたちでマシンルームなどと呼ばれる六畳くらいの部屋がある。窓ガラスで仕切られたこの部屋には箪笥や洗濯機くらいの大きさの装置が何台か置かれている。これがコンピュータ本体だ。もっともコンピュータが何台もあるわけではない。この箪笥が CPU でそっちの洗濯機がハードディスク,あの机に置かれているタイプライタが管理用コンソールといった具合に何台かある装置全部で一台のコンピュータになる。どこが〝ミニ〟だと突っ込みたくなるかもしれないが「六畳で収まるなんて,なんてミニ!」という時代のお話だ。
端末装置それぞれから(USB のご先祖様の)RS-232 という規格のアオダイショウみたいなケーブルが伸び,マシンルームに置かれたターミナルマルチプレクサと呼ばれるスーツケースに台数分のアオダイショウが刺さってコンピュータとの通信を行う。コンピュータと多数の端末装置を含めたこれら全体をサイトと呼び,root 権限を持って管理業務を行う人をシステム管理者あるいはスーパーユーザと呼んだ。
結構上手に説明できたと思うのだが雰囲気は伝わっただろうか。ここで重要なのは一台のコンピュータを数十人が一斉に使っていたという事実だ。洗濯機とかアオダイショウとかは,マアどうでもいい。
当時の UNIX の評価を一言で表すと〝自由で不安定な OS〟となる。メーカお仕着せではなく自分好みの「より良い環境」を作りあげる自由。さらに他のメインフレームやミニコン用 OS に比べると一般ユーザ権限でできることが圧倒的に多かった。そしてその代償が不安定さ。今では考えられないが UNIX のその不安定さゆえにプロ用 OS ではないと考える向きは多かったし「でも UNIX ってすぐ落ちるじゃん」というのは UNIX アンチ定番のディスりだった。UNIX の落とし方,みたいな情報がなんとなく廻ってきたものだ。
こういった雰囲気を鮮やかに伝えてくれるのが,高野豊『root から / へのメッセージ』(1991,アスキー)だ。当時アスキーが発行していた雑誌『UNIX MAGAZINE』に連載されていた氏のエッセイの1986年11月号から1988年10月号掲載分までをまとめた書籍である。著者の高野氏は勤務先の松下電器で1980年ごろから UNIX サイトのスーパーユーザを務めており,日本では最古参の一人である。この本の中で高野氏は繰返し UNIX の自由さと不安定さに言及している。すこし長くなるが,その中の一つを引用しよう。
CPU は,システムにとって重要な共有資源であるが,この CPU を実質的に停めてしまうことが UNIX ではいとも簡単にできる。たとえば,cc コマンドを10個くらい同時に走らせてみたらよい。VAX-11/780 といえども,同時に実行できるコンパイルはせいぜい3つか4つである。それ以上実行することも当然可能ではあるが,他に与える影響が無視できなくなる。つまり,てきめんに vi のカーソルが動かなくなる。あるいは,すこし大きめなディレクトリ上での ls コマンドの出力が表示されるまでに煙草を1本吸い終えてしまったり,タイムアウトでログインが撥ねつけられたりといったバカげた現象が起きだすのである。こういった状態になると,UNIX は破壊されたに等しい。真夜中,独りで VAX を占有して使っているのなら何をやろうとかまわない。しかし,20人30人と多数の人間が使っているときに勝手をやられると非常に困るのである。当人の仕事が遅れるのは自業自得だとしても,そのとばっちりで他のエディタまで止まってしまうと,もはやどの仕事も進行しなくなる。
ディスクについても同様なことがいえる。UNIX では,ファイルシステムを使いはたすまで大きなファイルを自由に作ることができる。したがって,自分のプロセスがいったいどのくらいの容量のファイルを作り出すのか見当もつけられないようなアマチュアが使うと悲惨なことになる。ディスクを使いはたすと,コンソール・タイプライターにエラー・メッセージが出力されるが,夜中にそれが発生して,コンソール・タイプライターが一晩中エラー・メッセージを打ち続け,朝マシンルームに行ってみると紙を一箱打ち尽くしてしまい,ピーピーと悲しげな声を上げて人を呼んでいた光景を私は何度も見てきた。こうなると,それをしでかした本人のプロセスは当然のこととしても,同じディスクで走っている他のプロセスも先に進めなくなってしまう。すこしでも負荷を夜間にまわそうとする善意は逆転してしまい,わずかでも仕事を先に進めようとする意図も完璧に打ち砕かれてしまうのである。
そして,こうした不安定さが「哲学」を必要としたのだ。自分が利用しているサイトに「cc コマンドを10個くらい同時に走らせ」たり「自分のプロセスがいったいどのくらいの容量のファイルを作り出すのか見当もつけられないようなアマチュア」がいるとその累は自分にも及んでしまう。だからサイトの利用者全員に UNIX の設計の基本的な考え方を理解してもらうことが,自分のために必要だった。UNIX の伝道がより苛烈だった理由のひとつがここにあるのだ。
ミニコン上で誕生した UNIX は 4.3BSD(1986)で最高潮を迎える。注意したいのはミニコン時代の UNIX は Research UNIX と CSRG BSD みたいな区別をせずにまとめて UNIX として扱われていたことだ。実際『プロフェッショナル UNIX』も『root から〜』も UNIX と記述されてはいるが実際には BSD を扱っている。べつに当時の人が無知だったわけではない。なにしろ BSD を利用するためにはまず AT&T から UNIX のライセンスを購入し,そのうえでカリフォルニア大学バークレー校(UCB)から BSD を入手しなければならなかったからその関係は当然広く知られていた。ベル研で発明された UNIX を外部の人たちも含めみんなで改良し,それら全体が UNIX であるという考え方が自然だっただけである。『Life with UNIX』のような英語の文献によく登場する “Berkeley UNIX” という言い回しが当時の気分をよく表している。UNIX vs BSD みたいな捉え方は法廷闘争を経た90年代以降の感覚だ。
もっともそういう70年代風味の牧歌的風景はミニコン世界限定の話であった。BSD そのものはミニコン用のものしかなかったが,そのコードを受け継いだ BSD 系 Unix や AT&T が推し進める System V などがワークステーション市場を舞台に80年代中盤から激しく覇権を争うようになる。いわゆる Unix 戦争で,PC 用 Unix であるマイクロソフトの XENIX も当然参戦した。ミニコン世界が牧歌的だったのは,ぶっちゃけていえば先のない技術だったからだ。ただ Unix 戦争はあくまでも標準という聖杯を争う戦いであり,AT&T と BSD 系 Unix の Sun Microsystems が共同で System V Release 4.0 (SVR4) を作りあげたように後の法廷闘争とは趣が違う。
こうしたミニコン UNIX からワークステーション Unix への転変は Unix そのものや文化にも変化をもたらした。まず激しい競争は Unix の高機能化を加速した。商品として判りやすい惹句が「あれもできます,これもできます」なのは誰もが知っている。もちろん安定性を増すために quota のような利用者の自由を制限する機能も含まれていた。またワークステーション Unix は現在の Unix 系 OS と同様同時に一人が使うものであり前述の布教の必要性は大幅に減じた。達人たちのみの楽園から万人に開かれた道具に変ったのだ。こういった変化を体感したければ『root から〜』と水越賢治『スーパーユーザの日々』(1993,オーム社)を読み比べてみるといい。『スーパーユーザの日々』はワークステーション Unix のシステム管理の入門書だ。この本ではたんに知識を羅列するかわりに架空のソフトウェアハウス(開発会社)を舞台に新卒社員が先輩社員からシステム管理を学ぶという体裁をとっており,そのおかげで架空の話とはいえ90年代前半の雰囲気が堪能できる。出版年でいえば『root から〜』と二年しか違わない『スーパーユーザの日々』の落差は “dog year” と称された当時の激烈な変化まで体感できるだろう。
当時はよくいわれたのに今やほとんど聞かれなくなったものがある。マキルロイの論文の結論部分に書かれたそれは,1973年に出版されたイギリスの経済学者エルンスト・シューマッハーの著作の題名で,中学生の英語力があれば十分に理解できる平明な一文だ。
Small is beautiful.
マキルロイは『人月の神話』を引いて一定の留保をつけてはいるものの,これが UNIX 哲学の背骨であることに違いはない。機能をありったけ詰め込もうとして失敗した “kitchen-in-a-sink” な MULTI•cs のアンチテーゼである UNI•x にとって,これ以上のスローガンがあるだろうか?
ひるがえって現在の Unix 系 OS をみれば,ブクブクと肥え太ったシステムコール,全容を俯瞰するだけでも一苦労するライブラリインターフェイス,一生使うことのないオプションスイッチまみれのコマンド群。UNIX が仮想敵とした OS そのものだ。そのことについてとくになにも思わない。ハードウェアは長足の進歩を遂げ,コンピュータの応用範囲は途方もなく拡がった。UNIX が変らなければたんに打ち棄てられ,歴史書を飾る一項目になっただけだ。ただ現在「UNIX 哲学」を語るならそうした背景は理解していなければならないし,どれだけ繊細な注意を払ったところで〝つまみ食い〟になってしまうことは自覚すべきだ。
2022年7月中旬時点での情報。公式Youtubeチャンネルや公式サイトtv.peacelink.live上で探した際に見つけやすい形で堂々と出演していた日本人たちをリストアップ。そのため精度が高い情報ではない。
https://www.youtube.com/channel/UCrgyZY2ywXsTWjzAWKnjEcg
https://tv.peacelink.live/home
2021年9月12日「THINK TANK 2022 希望前進大会」にてビデオ演説。2022年2月13日「ワールドサミット2022・韓半島平和サミット」にて書面演説。https://anond.hatelabo.jp/20220713090656
イベント出演時には(安倍晋三ほどではないが)日本代表のVIP(2番手?)として扱われている。紹介時の肩書きは「第31代日本参議院議長」。出演回数は3回以上。
韓半島平和サミット開幕式(出演部分だけを切り抜いた公式動画) https://www.youtube.com/watch?v=fIsTxkGlo6g
[World summit] 월드서밋 2020 KINTEX 다테 추이치 (Hon. Chuichi Date 伊達 忠一)일본 전 참의원 의장 세계평화정상연합 총회 (ISCP) 연설
[World summit] 월드서밋 2020 KINTEX 다테 추이치 (Hon. Chuichi Date 伊達 忠一)일본 전 참의원 의장 환영만찬 연설
イベント出演時には(安倍晋三ほどではないが)日本代表のVIP(3番手?)として扱われている。紹介時の肩書きは「第26代日本環境大臣」。出演回数は2回以上。関連組織「世界平和議員連合(IAPP)」の議員連盟会長でもある。
韓半島平和サミット開幕式(出演部分だけを切り抜いた公式動画) https://www.youtube.com/watch?v=OwYAuMQ752w
[第3回THINK TANK 2022 フォーラム] 日本専門家の質疑
韓国から日本への映像中継の進行役として登場。「日本の国会の議員です」と自己紹介している通り現衆議院議員。大物の現役政治家としては安倍晋三と高木宏壽の二人だけ。
韓半島平和サミット開幕式 https://www.youtube.com/watch?v=f2ricogBBbE&t=6906s
紹介時の肩書きは「第70-71代防衛庁長官」。「小野義徳」という表記もあった。出演回数は3回以上。
[第1回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第4回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第2回THINK TANK 2022 フォーラム] 日本専門家の質疑
紹介時の肩書きは「元国連軍縮担当事務次長」。出演回数は2回以上。
[第1回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第4回THINK TANK 2022 フォーラム] 日本専門家の質疑
紹介時の肩書きは「第36代自衛艦隊司令官」。出演回数は2回以上。
[第2回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第4回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第1回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第1回THINK TANK 2022 フォーラム] 日本専門家の質疑
「30人ほどの議員があつまっている」と紹介しており、中継映像内に10人ほどの議員っぽい人たちが映る。
柳本卓治。松本文明。小林興起。中継で映っていた人たちの残り6人ほどは名札も見えず誰なのか判別できなかった
[World summit 2020] Mr. Yoshitaka Ishi_Former President, Kyushu Railway Company_세계평화경제인대회 (IAED)
[第3回THINK TANK 2022 フォーラム] 日本専門家の質疑
[第2回THINK TANK 2022 フォーラム] 日本専門家の質疑
[World summit] 월드서밋 2020 KINTEX_요시미츠 니시카와 (Yoshimitsu Nishikawa)일본도쿄대 글로벌·지역학부 교수 세계평화학술대회 (IAAP) 연설
Yuya Watase (Executive Director of The Washington Times Japan)。
など
CoreKeeper側で apt に依存しているっぽいので、Ubuntu でやった方が楽だと思います。
Ubuntu 20 TLS でやる場合、/home/steam/Steam/ が /home/steam/.steam/ になってたと思うので、環境に合わせて読み替えてください。
dpkg --add-architecture i386 add-apt-repository multiverse apt-get update apt-get dist-upgrade reboot
useradd -m steam passwd steam gpasswd -a steam sudo
sudo -u steam -s cd sudo apt install steamcmd ln -s /usr/games/steamcmd steamcmd ./steamcmd +login anonymous +app_update 1007 +app_update 1963720 +quit
cd ~/Steam/steamapps/common/Core\ Keeper\ Dedicated\ Server/ ./_launch.sh
Press Ctrl + C for Stop Core Keeper Dedicated Server
mkmir -p -m 775 /home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/worlds chown steam:steam /home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/worlds
Copy old world file (0.world.gzip) to
/home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/worlds
Copy old setting file (*.json) to
/home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/
chmod 664 /home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/worlds/0.world.gzip chmod 664 /home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/*.json
vi /etc/cron.hourly/corekeeper_backup #!/bin/bash cp -a /home/steam/.config/unity3d/Pugstorm/Core\ Keeper/DedicatedServer/worlds/0.world.gzip /home/steam/worldbackup/0.world.gzip.`date '+%Y%m%d%H%M%S'` cp -a /home/steam/Steam/steamapps/common/Core\ Keeper\ Dedicated\ Server/CoreKeeperServerLog.txt /home/steam/worldbackup/CoreKeeperServerLog.txt.`date '+%Y%m%d%H%M%S'` chmod 777 /etc/cron.hourly/corekeeper_backup sudo -u steam -s cd mkdir worldbackup
sudo -u steam -s cd ~/Steam/steamapps/common/Core\ Keeper\ Dedicated\ Server/ nohup ./_launch.sh tail -f ~/Steam/steamapps/common/Core\ Keeper\ Dedicated\ Server/CoreKeeperServerLog.txt
利用者の問題か、サーバーの問題かわかりませんが人数が10人超えると CPU4コア/メモリ4G/100Mbps で結構ラグかったです。
今は CPU6コア/メモリ8G/1000Mbps で動かしています。
6-8人以上で2-3時間サーバー動かしてると、Unityのライブラリがsegfault起こして、Core Keeper Dedicated Server が落ちます。
ログ取れたのでバグレポしましたが、改善するまでは不特定多数が好き勝手するサーバーみたいなのを長期運用するのは厳しいかなと思います。タイミングによってはアイテムロストしてしまうので。
↓
↓
降伏or和平
↓
フィンランドがNATO加盟申請して効力が出る(集団防衛義務)までの間にロシアに攻撃される可能性が危惧されているが、これは北大西洋条約第10,11条のため。
Article 10
The Parties may, by unanimous agreement, invite any other European State in a position to further the principles of this Treaty and to contribute to the security of the North Atlantic area to accede to this Treaty. Any State so invited may become a Party to the Treaty by depositing its instrument of accession with the Government of the United States of America. The Government of the United States of America will inform each of the Parties of the deposit of each such instrument of accession.
締約国は、この条約の原則を促進し、かつ、北大西洋地域の安全に貢献する地位にある他のヨーロッパの国に対し、この条約に加入するよう全員一致の合意により招請することができる。このようにして招請された国は、その加入書をアメリカ合衆国政府に寄託することによつてこの条約の締約国となることができる。アメリカ合衆国政府は、その加入書の寄託を各締約国に通報する。
Article 11
This Treaty shall be ratified and its provisions carried out by the Parties in accordance with their respective constitutional processes. The instruments of ratification shall be deposited as soon as possible with the Government of the United States of America, which will notify all the other signatories of each deposit. The Treaty shall enter into force between the States which have ratified it as soon as the ratifications of the majority of the signatories, including the ratifications of Belgium, Canada, France, Luxembourg, the Netherlands, the United Kingdom and the United States, have been deposited and shall come into effect with respect to other States on the date of the deposit of their ratifications.
第十一条
締約国は、各自の憲法上の手続に従つて、この条約を批准し、その規定を実施しなければならない。批准書は、できる限りすみやかにアメリカ合衆国政府に寄託するものとし、同政府は、その寄託を他のすべての署名国に通告する。この条約は、ベルギー、カナダ、フランス、ルクセンブルグ、オランダ、連合王国及び合衆国の批准書を含む署名国の過半数の批准書が寄託された時に、この条約を批准した国の間で効力を生じ、その他の国については、その批准書の寄託の日に効力を生ずる。
つまり、加盟希望国が加盟できるのは既加盟国の招聘により、その招聘は既加盟国の全員一致が原則。
だからロシアには緊張を高めるために国境を侵犯して紛争を起こし紛争国にしてしまうという手がある。
またロシアは各国の極右を手先にしていて彼等はプーチンロシアの利益と自国が孤立して得られる利益の為に動く。反国際主義だがロシアは別なのだな。仏の大統領選次位のルペンもこれに含まれる。更にルペンはNATO離脱派だ。
過去の中欧加盟では加盟には結構なプロセスを踏んでいて、希望国は根回し外交や平和維持軍への派兵等の域外活動に参加したりした上で全員一致の承認を得ている。
なのでロシアと対立状態にあるフィンランドの加盟は難航するしその間にロシアが何するか判らなくて危険。
だったら冒頭みたいな無茶しないと紛争に持ち込まれちゃうわけよ。
このアイデアだったらある日いきなりNATO軍が領内に居るから手を出せないし講和と同時に軍事同盟加盟は不自然じゃない。
フィンランド人の血が流れたらそれが原因で加盟も流れちゃうのだから無駄死にになってしまう。だからこのブリリアントなアイデアしかないのだ。
ま~でもロシアの歴史的に、多方面で利の無い戦争継続してたら内乱で皇帝が処刑される、臨時政府が打倒されるってのがパターンなのだが。動員せずに戦争じゃなくて特別軍事作戦と言ってるのもそのせいでしょ。
いや、おまえオウサマペンギンじゃん。