2025,江端さんの忘備録

江端家では、家族のだれかがNetflix(以下、ネトフリ)のコンテンツを見たくなったら、1ヶ月間のみ契約する方式を採っています。
In the Ebata household, whenever someone wants to watch something on Netflix, we adopt a one-month-only subscription method.

この方法は簡単です。ネトフリに契約し、その後、すぐに解約するだけ。これで、1ヶ月間だけネトフリが利用できます。
It's simple: you subscribe to Netflix, then cancel immediately. That way, you can still use it for the rest of the month.

Netflix の解約手順(日本向け)

で、だれが見ていたのか分からないのですが(リビングが無人だったので)、ネトフリで「そろばん大会」に密着したドキュメンタリー番組が流れていました。
I’m not sure who had been watching it (the living room was empty), but a Netflix documentary covering a "soroban (abacus) competition" was playing.

-----

以前も書きましたが、江端家では「最高の習い事は“そろばん”だった」という見解で、家族全員の意見が一致しています。
As I’ve mentioned before, in the Ebata family, we all agree that the best extracurricular activity was “soroban” (abacus training).

―― 自分の頭の中に電卓を実装する。
—Implementing a calculator inside your brain.

それが本当にできてしまうからです。しかも、キー入力もディスプレイ表示も不要の電卓。
Because you can do it, and it’s a calculator that doesn’t require keys or a display.

これをシステムエンジニア的に言えば、「脳内に電卓のDockerコンテナを搭載する」ようなものです。
From a systems engineer’s perspective, it’s like running a calculator as a Docker container inside your brain.

(今も学校でやっているか分かりませんが)計算ドリルなどは、アニメを見ながら数値を書き写すだけで済み、1冊1時間程度で終わったと思います。
(I’m not sure if they still assign them in schools,) However, calculation drills could be completed by simply copying numbers while watching anime, finishing a whole book in about an hour.

また、スーパーのレジに並ぶ前に、支払い金額の計算も終わらせていました。
Also, before even reaching the register at the supermarket, we’d already mentally calculated the total bill.

極大/極小値などの煩雑な計算時間も、すべて無視できるようになります。
Tedious calculations for maxima and minima, for example, can be ignored entirely.

何度も書いてきましたが、これは「計算作業が不要になる」ということであり、「数学的思考だけが必要となる」という意味で、真の意味での数学の学びが可能になります。
As I’ve said many times, it means the mechanical task of calculation becomes unnecessary, allowing one to focus purely on mathematical thinking—enabling authentic learning in mathematics.

これは、システムエンジニアである私(江端)の公式見解です。
This is my official opinion—as a computer specialist.

私なら、プログラミング教育よりも、まずそろばん塾に子どもを叩き込みますし、実際にそうしてきました。
If it were up to me, I’d send kids to soroban school before teaching them programming—and in fact, I did precisely that.

そして、“完璧に元は取った”と確信しています。
And I’m convinced it paid off perfectly.

まあ、あまり良い例ではないですが、最終学歴の定量的評価(偏差値)において、私たち夫婦は、娘たちに「完敗」しています。
Though perhaps not the best example, in terms of quantitative academic achievement (standardized scores), my wife and I were thoroughly defeated by our daughters.

もちろん、そのすべてが「そろばんのおかげ」だとは言いませんが、少なくとも「計算という苦痛」からは解放させてあげられた、と自負しています。
Of course, I won’t claim Soroban deserves all the credit, but I do take pride in having freed them from the suffering of arithmetic.

-----

「そろばん大会(珠算競技大会)」のドキュメンタリーに話を戻しますが、正直、「すごいものを見た」と思いました。
Returning to the documentary on the abacus competition, I must say, I was genuinely impressed.

私が見たのは、読上算や見取算の競技で、解答用紙にすべての問題を解き終えた人が、早押しボタンを押す形式でした。
What I saw were competitions in oral arithmetic and mental math, where participants pressed a buzzer after completing their answer sheets.

そろばんが登場していなかったので、暗算競技(特に「かけ算」や「わり算」に特化した部門)だったと思います。
There were no actual abacuses used, so I assume it was the mental arithmetic division, especially focused on multiplication and division.

珠算式暗算とは、「そろばんの珠の動きを頭の中でイメージして行う暗算」です。
Soroban-style mental calculation means imagining the movement of abacus beads in your head to perform arithmetic.

競技開始の合図で、参加者は用紙をめくり、すぐに頭の中で数字を動かし始めます。
At the signal to start, participants flipped over their sheets and immediately began mentally shifting numbers.

指や唇を動かす者もいれば、完全に無表情で脳内だけで珠を動かす者もいます。
Some moved their fingers or lips; others remained completely expressionless, moving beads only in their heads.

問題数が多いため、早く終わらせるには、珠算式暗算のスピードと正確さが必須です。
Due to the large number of problems, speed and precision in soroban-style mental math were crucial for completing tasks quickly.

数十秒後、最初の「カチッ」という音が響くと、選手たちに緊張が走ります。
A few dozen seconds in, the first “click” of a buzzer echoes, and tension ripples through the remaining contestants.

全員が解答を終えると採点が行われ、1位は「最速かつ全問正解」の者に与えられます。
Once everyone finishes, scoring begins. First place goes to the person who finishes fastest with all answers correct.

問題の内容は、4桁×4桁のかけ算や、6桁÷2桁の割り算だったようでした。
The problems appeared to involve tasks such as 4-digit by 4-digit multiplications and 6-digit divided by 2-digit divisions.

とにかく『見ていてドキドキしました』。
In any case, it had me on the edge of my seat.

正直、陸上の選手が、相撲取りが、大リーグの日本人選手が、フィギュアスケーターが、フードファイターが、どんなパフォーマンスをしていても、この「ドキドキ」には及びません。
Honestly, no matter what performances I see—track athletes, sumo wrestlers, Japanese players in the MLB, figure skaters, or competitive eaters—none of them gave me this same kind of excitement.

-----

なんでかな、と考えてみたのですが、
I thought about why that might be the case...

―― ちょっとだけでも、自分の人生の一部に「かすったことがあるモノ」
—Maybe it's because it’s something that even slightly brushed against my own life at some point.

というのがポイントなのだと思います。
I think that’s the key.

これらの競技に意味があるか?という問いは、すでに愚問です。そしてそのような問いは、むしろ『下品』ですらあると言えるでしょう。
Asking whether these competitions “have meaning” is already a foolish question—and I’d even say such a question is vulgar.

そこに「ドキドキ」があるのであれば、それだけで十分な価値がある。そのような考え方が「正解」であり「上品」だと私は思います。
If there’s “excitement” there, then that alone gives it value. That kind of thinking is, I believe, the correct—and refined—way to see things.

そして、自分が全く理解できない「ドキドキ」であっても、それをちゃんと価値あるものとして認めていくことは、きっと「人間」として、とても大切なことだと思うのです。
Even if you don’t understand someone else’s excitement at all, acknowledging it as something valuable is probably an essential part of being human.

-----

まあ、自分しか理解できない「ドキドキ」であっても、駅の階段を駆け上がるときとか、健康診断で「要再検査」を見たときの「ドキドキ」は、正直、いらないんですけどね。
That said, even if it's a kind of “excitement” only I understand, the kind you get when running up the stairs at the train station or when seeing “requires re-examination” on a health checkup report—yeah, I could do without those kinds of thrills.

―― 『漢字はググればいい。計算は電卓使う。学校で勉強する必要がない』の仮説は棄却された("失敗した")

 

未分類

✅ Netflix の解約手順(日本向け)

① Netflix公式ウェブサイトでの解約(一般的な方法)

 

  1. Netflix に ウェブブラウザからアクセスして ログイン
     ※スマホアプリやテレビアプリからは解約できませんTom's Guide+11Netflixヘルプセンター+11MovPilot動画ダウンローダー - ストリーミング動画を自由にダウンロード+11

  2. プロフィールアイコンから「アカウント」を選択

  3. メンバーシップのキャンセル」をクリック

  4. キャンセル手続きの完了」を選択し、解約を確定

  5. 登録メールアドレスに「キャンセル完了」の確認メールが届きます

ちょっと油断していると、「キャンセル」をキャンセルされるようにUI(ユーザインターフェース)が設計されているので、注意のこと

2025,江端さんの忘備録

ある店舗を出店する際、マーケティングリサーチ(アンケート調査を含む)を行うのが常道です。
When opening a new store, conducting marketing research—including surveys—is standard practice.

ただ、このアンケート調査には、十分なサンプル数がないと有意性が疑われ続けるという、悩ましい問題があります。―― ぶっちゃけて言えば「金と時間」です。
However, a troubling issue is that unless you have a sufficiently large sample size, the statistical significance will always be questioned—frankly, it comes down to "money and time."

アンケート調査は、金と時間がかかる(本当にびっくりするくらい高い)。
Surveys require both money and time (and they can be shockingly expensive).

そして、その割に内容が信用できない。
And despite the cost, the results often feel unreliable.

なぜ、"私"が"そう"思うのか。
Why do I think that way?

"私"は、真面目にアンケートに答えないからです。
Because I don’t answer surveys honestly.

-----

(1)アンケート項目の端(「とても良い」「とても悪い」)にはチェックを付けない
(1) I never choose the extreme ends of the scale (like "very good" or "very bad").

(2)対象者の顔を思い浮かべて、真ん中(「普通」)は避け、少し上にチェックを入れる
(2) I picture the person the question refers to and avoid selecting the "neutral" middle, usually going slightly above average.

(3)そもそも質問文を真面目に読まず、単語を2~3拾うだけで済ませる
(3) I don’t even read the whole question seriously—pick up a couple of words and move on.

そして私は、「アンケートの匿名性」も信じていません。匿名を担保する条件が明記されていないアンケートなんて、信用できるわけがない。
And I don’t believe in the so-called "anonymity" of surveys. If the conditions for anonymity aren’t clearly stated, how can anyone trust them?

たとえば「部署単位で統計を取る」と言われれば、「3人しかいない課で匿名性を担保する」も入るわけで、こんなアンケートはもはやコントです。
If I’m told the results will be broken down by department, and my team has only three people, that’s no longer anonymous—it’s a joke.

サンプル数を開示しないアンケートも信用ならないし、実際、「アンケートに答えたあとで社長に呼び出された」という話を、私の人生で最も近い人から直接聞いています。
Surveys that don’t disclose their sample size can’t be trusted either. And I’ve personally heard—from someone very close to me—that the CEO summoned them after responding to a survey.

そんなリスクを負ってまで、アンケートなんぞに答えるものか。金(報酬)も出ないのに。
Why on earth would I take that risk, especially when I don’t even get paid for it?

-----

それに、アンケートが「リアルタイムで行われない」という点も大きな問題です。
Another significant issue is that surveys are often not conducted in real-time.

私の見解では、「対象(イベント等)から2~3日後のアンケート結果は“ゴミ”」です。
In my opinion, any survey conducted 2–3 days after the event is “garbage.”

2~3日も経てば、参加者の頭はイベントから離れ、「いわゆるセルフプレジャー後の賢者モード」に入っています。そんな状態で出された回答など、当てになる訳がない。
After a few days, participants are emotionally detached—they’ve entered what you might call a "post-self-pleasure enlightenment mode." Responses from that state are useless.

私の見解に異議がある方は、どうぞチャレンジして下さい。ロジックと経験とデータでお迎えします。
If anyone wants to challenge me on this, I'm ready. I’ll welcome you with logic, experience, and data.

-----

もちろん、アンケート一つ一つは"ゴミ"でも、"ゴミ"が集まれば一定の傾向は読み取れます。
Of course, even if individual survey answers are "garbage," aggregating enough of them can still reveal patterns.

上記(1)~(3)のような傾向を持つ被験者を除外したり、逆に傾向補正したり、処理の工夫もできます。
You can exclude respondents with tendencies like (1)–(3), or apply corrective weighting—there are ways to process the data.

要は、アンケートは「十分な母数」があって、そこからバイアス層を除いても「なお残る母数」がある場合にだけ意味を持ちます。
Ultimately, surveys only have value if the initial sample size is large enough to eliminate biased responses while still leaving a sufficient number.

つまり、話は最初に戻ります――「金と時間」です。
This brings us back to the original point: "money and time."

-----

私なら、コンビニの出店計画を立てるなら、住民にアンケートなんぞ取らず、近隣の住民や店舗の店主、あるいは似た地域特性を持つコンビニの店主に直接ヒアリングします。
If I were planning to open a convenience store, I wouldn’t bother surveying residents. I’d directly interview local shop owners, nearby residents, or store managers in similar neighborhoods.

彼らは、毎日の人の流れを見つづけています。
They observe the flow of people every single day.

―― 被験者本人より、その本人のことが見えているから
—They know more about the people than the people know about themselves.

です。

バスや鉄道の利用者動向が知りたいなら、利用者にアンケートを取るよりも、バスの運転手や駅員にヒアリングした方がずっと早い。
To understand bus or train ridership trends, forget about the passengers—ask the drivers or station staff. Much faster.

彼らの視点なら、「月曜朝の乗客の顔色」「歩き方の覇気」「金曜夜のテンション」「水曜の疲れ具合」など、マインドまで読み取れる。
From their perspective, you can read people’s moods—like facial expressions on Monday mornings, their energy when walking, the Friday night vibe, or midweek fatigue.

何より「安くて早い」。
Above all, it’s cheap and fast.

つまり、私が言いたいのはこうです。
So here’s what I’m trying to say:

―― 自分のことは、他人の方がよくわかっている
—Other people know more about you than you do yourself.

自己評価と他者評価が割れるとき、信じるべきは「他人」であって、「自分」ではない。
When self-evaluation and others’ evaluation don’t match, trust the others—not yourself.

この当たり前が、意外と世の中では理解されていない気がします。
Many people surprisingly misunderstand this obvious truth.

-----

アンケートを取るなら「自分」ではなく「他人」を対象にすべきです。その方が信頼性の高いデータになります。
If you must run a survey, target people other than the subject. That way, the data is much more reliable.

たとえば、こんな質問に変えるとよいでしょう。
For example, rephrase the questions like this:

「(自分ではないが)自分の部署には、上司を嫌っている人が(少ない・普通・多い)」
“(Not me, but) there are people in my department who dislike our boss. (Few / Some / Many)”

「(自分ではないが)会社の方針を理解していない人が(少ない・普通・多い)」
“(Not me, but) there are people who don’t understand the company’s direction. (Few / Some / Many)”

このように「他人の観察」に質問をすり替えれば、ずっと本音に近づきます。
If you reframe the questions to focus on observing others, you’ll get answers much closer to the truth.

-----

つまり――
In short—

「自己開示を求められるアンケートで、本当に自己開示する人間など、基本的にいない」
“No one really opens up on a survey that demands self-disclosure.”

という、この当然の理屈を分かっていないところが、アンケートの最大の問題点なのです。
Failing to grasp this simple fact is the biggest flaw in how surveys are designed.

という訳で、意義のあるアンケートの例としては、「会社を辞める前日に行うアンケート」くらいじゃないかな、と思う訳ですよ。
So in the end, I’d say the only significant survey… is the one you conduct the day before someone quits their job.

『自分の仕える主人(例:首相)の主張に反することは、(どう考えていようが)口にしない』――

 

未分類

江端さんのひとりごと 「神の火」

江端さんのひとりごと「神の火」から、以下一部抜粋

=====

話はちょっと変わりますが、何年か前、動燃(動力炉核燃料事業団)が、事故の隠蔽を図り、何度も嘘の上塗り繰り返し、その都度、嘘が見つけられ、その度に謝罪会見をしていた、見苦しいことこの上もない愚劣な行為を繰り返していたことがあります。

この時、私は「こりゃ、いいなあ」と思いました。

まず嘘をつく。

嘘が見つかったら謝る。

見つからなければ黙りつづける。

正直に言っても、どっちみち怒られるなら、黙っていて見つからないほうに賭ける。

これは、公に責任を持たない利己的な個人の理論としては、正しいと思いますが、いったん壊れたら最後、周辺地域を死滅させる原子力を管理する公の機関が、まあなんということか、この理論で動いている。

その為に民草たる民衆の命なんぞは後回しにして、自己保身のために動き、 最後まで謝罪を渋り、謝罪した後は、我々の血税から賠償金の支払いをする。

何の邪心も憤りもなく、心から素直に『やっぱり、体制サイドは、おいしい なあ』と、羨ましく思ったものでした。

閑話休題

=====

2025,江端さんの忘備録

事故(セキュリティ事故を含む)が発生した場合、私たちサラリーマンは基本的に会社への報告が義務づけられております。
When an incident (including a security breach) occurs, we, as corporate employees, are generally obligated to report it to the company.

しかし、そのような報告をすれば、叱責と処分と膨大な手続きが必要となります。しかし、報告せずに発覚すれば、社会人人生を終わらせかねないことにもなります。
However, making such a report often leads to reprimands, disciplinary action, and a mountain of paperwork. Still, if the incident comes to light without a report, it could mean the end of one's professional life.

この場合、ゲーム理論を持ち出すまでもなく、事故を起こした社会人の取る最適戦略は、
Even without invoking game theory, the optimal strategy for a working adult in such a case is:

ーー 報告せずに、発覚しない方に賭ける
— Do not report it, and bet on it never being discovered.

です。
That’s it.

これは、会社にはもちろん、本人にとっても悪手になることは分かっていますが、それでもローカルミニマムな最適化である、という事実は揺らぎませんが ーー サラリーマンとしての私は、この話に、これ以上ツッコんで話をしたくありませんので、この話はここまでとします。
We all know that this is a bad move — for both the company and the individual — and yet, it remains a locally optimized minimum. And as a salaryman, I don’t want to dig into this any further.

-----

ところが最近、「あ、その手があったか」と思うような事例がありました。
However, recently, I came across a case that made me think, “Ah, that’s one way to handle it.”

このような事故を担当する責任者が、自ら自分のやってきた事故を暴露し、それについての経緯を語ったのです。
The person responsible for the incident voluntarily came forward and revealed their own mistake, recounting the entire story.

これは、結構、私の心にヒットしました。
This hit me quite hard.

「恥ずかしいし、怒られたし、いろいろなところに頭を下げにいったし、膨大な報告書も書かされて、大変な苦労をした」という話を、その本人から「自分ごと」として聞かされたことが、私の「事故報告」のしきい値を随分下げました。
Hearing that person say, “It was embarrassing, I got scolded, I had to apologize all over the place, and I was forced to write endless reports—it was a nightmare,” as a personal story, lowered my threshold for making such reports.

「報告せずに、発覚しない方に賭ける」というローカルミニマムを破るには、この、会社の“公”の業務命令ではなく、本人の“私”の体験の告白が一番効果があると思いました。
To break free from the local minimum of “betting on nondiscovery,” I realized that not an official company directive, but a personal confession from someone who’s been through it, is what works best.

「生きている限り、誰でも事故を起こす。それは仕方がない。私だって、いろいろとやらかしてきた。だから『報告』を必要以上に恐れるな」というメッセージを送ることが大切だと思うんですよね。
“As long as we live, anyone can make mistakes. It’s inevitable. I’ve messed up plenty myself. So don’t be overly afraid of reporting.” — I think that kind of message is essential.

-----

で、まあ、私が会社で「現在、“うつ”で“不眠症”で、“アルコール依存症”だった」と公言しているのは、『私“だけ”は、“それ”を責めない』という意思表明でもあるんです。
So, the reason I openly say at work that I am currently “depressed,” “insomniac,” and “alcohol-dependent” is to declare: ‘I, at least, will not blame you for that.’

実際に会社で、何人かが“うつ”について愚痴(本当にやっかいな病気)を語ってきました。そりゃ、“うつ”の愚痴を言うなら“うつ”に悩んでいる人が、一番安心でしょう。
Several people at the company have come to talk to me about their struggles with depression (which is a troublesome illness). Of course, if you're going to complain about depression, the safest person to talk to is someone who's been through it.

私、この手の話が多くの人にもっと気楽にできるように、自分の病気や事件や事故について、会社や大学の公的な場で、いろいろぶちまけてきました。苦しいことを誰かに言える環境は、きっと良い環境だと思うのです。
Wanting to make this kind of conversation easier for others, I’ve openly shared my illnesses, incidents, and mishaps in formal settings at work and university. I genuinely believe that an environment where you can talk about your pain is a good environment.

-----

ですが、私が「“うつ”で“不眠症”で“アルコール依存症”」という話題の後に、「実は自分も……」と話が続きません。
And yet, after I bring up my “depression,” “insomnia,” and “alcohol dependency,” no one ever follows up with, “Actually, me too…”

なぜでしょうか?
Why is that?

ちょっと考えてみたのですが、
I gave it some thought.

ーー 私(江端)が“うつ”で“不眠症”で“アルコール依存症”であることは、別段、特別なことではない
— Maybe the fact that I (Ebata) am depressed, insomniac, and alcohol-dependent just doesn’t strike anyone as particularly surprising.

と思われているんじゃないか、と気づきました。
That’s the impression I’ve come to suspect people have.

-----

私が何をやらかそうとも、それは私の事件として閉じてしまうのであれば、私のやってきたことは何だったのか?
If whatever I say or do is seen as just another “Ebata thing,” then what has everything I’ve done amounted to?

『自分のプライバシーの切り売り』という言葉が浮かび上がって、今、あわてて消している最中です。
The phrase “selling off my privacy” popped into my head—and I’m now frantically trying to erase it.

『江端さんのひとりごと「神の火」』から、以下一部抜粋

 

2025,江端さんの忘備録

先日、テレビで何かのトーク番組を見ていました。
The other day, I was watching a television talk show.

「仲間とともに“美味しい”と評判の牛タンの店に入り、皆で『美味しいね』と言い合いながら和気藹々と食事を楽しんでいたところへ、『◯◯さん、俺、これよりもっと美味い牛タンの店、知ってますよ』などと言い出した奴がいて、せっかくの食事が台無しになった」という話を耳にしました。
I heard a story about someone who, while dining happily with friends at a well-reviewed beef tongue restaurant, ruined the mood by saying, "Hey, I know a place that serves even better beef tongue."

うん、こういう奴、私も一人、知っています。
Yeah, I know someone exactly like that.

-----

親戚の若い娘が、世間的にも取得が難しいとされている国家資格を取ったと聞き、私は「本当にすごい」と素直に思い、かなりの額をお祝いとして渡しました。
When I heard that a young relative of mine had passed a nationally recognized qualification exam, one that's notoriously difficult, I was genuinely impressed and gave her a considerable amount of money as a congratulatory gift.

親戚の集まりで、私が『よくがんばったよな』と彼女を褒めていたら、
At a family gathering, while I was praising her, saying, "You really worked hard, didn’t you?"

『その資格取得者、私の職場に何人もいますけど?』
Someone chimed in: "We have tons of people with that qualification at my office."

といった奴がいました。
Yes, that kind of person.

-----

そいつとは、それ以降、一度も顔を合わせていません。会いたいとも思いません。
I haven't seen that person since. Nor do I have any desire to.

後に、職場でうまくいかず、心の病を患ったという話を風の便りに聞きましたが――私の中には、何の感情も湧きませんでした。
Later, I heard through the grapevine that things didn’t go well at work, and they had developed a mental illness, but I felt absolutely nothing.

まあ、奴のことはどうでもいいんです。どうせ、二度と会うこともないでしょうから。
Well, I don’t really care about them anymore. I’m never going to see them again anyway.

これらの出来事を通じて、私は「自分もまた、誰かの気持ちを台無しにするような言動をしていないか」と、自己チェックをしなければならないと思いました。
Through these experiences, I realized I need to take a step back and check myself. Have I said things that ruin someone else’s feelings?

私が“うつ”と“不眠”を患っているのは、ひょっとすると、自分の中にも、同じような因子があるからかもしれない――そう思うと、少し背筋が冷えます。
The fact that I suffer from depression and insomnia maybe that’s because I carry the same kind of traits within me. That thought sends a chill down my spine.

-----

私が、こういう奴の多くを1秒で切り捨ててきたように、たぶん私も、多くの人から、1秒で切り捨てられてきたのでしょう。
Just as I’ve dismissed people like that in a single second, I’ve probably been dismissed by many others in just the same way.

「1秒で切り捨てられて当然のことをした」のであれば、1秒で切り捨てられるのは、ある意味当然です。
If I did something that warranted being cut off in a second, then perhaps I deserved exactly that.

しかし、それより深刻なのは、「1秒で切り捨てられて当然のことをした」ことに気づかないまま、人生を転げ落ちていくことです。
But what’s even more serious is rolling downhill in life without ever realizing you’ve done something that deserved such a swift rejection.

そして、そういう人間に対する、もっとも簡単で、もっとも確実な報復は――
And for people like that, the simplest and most certain form of revenge is?

「何もしないこと」です。
Doing nothing.

そのまま放置して、そいつが静かに破滅していくのを、ただ黙って見ていればいいのです。
Just leave them be, and quietly watch as they ruin themselves.

私の人生の中に、何人かそういう人間がいました。私は彼等を放置しました。そして破滅していくのを見ていました。―― 静かに、無感動に。
There have been a few such people in my life. I left them alone. I watched them fall apart -- quietly, without emotion.

まあ、私も「破滅している側」の一人かもしれませんが。
Well, I might be one of the ones falling apart, too.

未分類

殺人事件の被害者についての近所の人へのインタビューは「明るくて、礼儀正しい人だった」というものが多いですが、統計的に、殺人事件の被害者が必ず「明るくて、礼儀正しい人だった」とは私には思えないのです。これはいわゆる偏向報道ではないでしょうか

あなたの疑問は極めてもっともで、実際、そのような報道パターンには認知バイアスメディア報道の構造的な偏りが関与しています。以下、その背景をいくつかの観点から整理します。


1. 「偏向報道」といえるか

はい、**報道傾向としての偏り(bias)**があることは否定できません。ただし、意図的な「情報操作」ではなく、取材現場の構造的な限界や、視聴者の受容傾向に合わせた「構造的バイアス」と考えられます。


2. なぜ「明るくて礼儀正しい」となるのか

  • 取材対象者の選別バイアス
     メディアがインタビューするのは、比較的「話しやすい」「協力的な」近隣住民に偏るため、肯定的なコメントが出やすい。

  • 社会的圧力と無難な表現
     被害者を悪く言うことは、道徳的にもリスクがあり、結果として誰もが言いやすい「明るい」「礼儀正しい」という定型句が選ばれる。

  • ニュースの物語化
     ニュース報道では「理不尽な事件」という構図を作るために、被害者を“非の打ち所のない存在”として描写する傾向がある。


3. 統計的にはどうか?

報道からは「被害者はみな善人だった」という印象を受けるかもしれませんが、実際には殺人事件の背景には、

  • 暴力団関係者間の抗争

  • 家庭内暴力やDVのもつれ

  • 過去のトラブルや犯罪歴

など、被害者と加害者の関係性が複雑なケースも少なくありません。こうした事例は報道される際に、「詳細は控える」または事件の構造の方に焦点が移るため、被害者像が一面的に処理されることがあります。


4. 報道の信頼性と視聴者の態度

「またか」と思っても、視聴者の多くは「悪く言う人がいないってことは本当に良い人だったのだろう」と納得してしまい、疑問を抱かないまま報道が成立してしまいます。この点で、報道が視聴者の期待に寄り添った形で反復されているとも言えます。


まとめ:これは偏向報道か?

  • 事実の取捨選択による構造的偏向は存在する

  • 明示的な情報操作(虚偽)とは限らない

  • 🧠 視聴者側の期待・感情もバイアスを後押ししている


よって、「被害者はいつも明るくて礼儀正しい」という報道の繰り返しは、メディアのナラティブ構築の一環であり、報道の限界と視聴者心理の合作と言えるでしょう。あなたのように疑問を持つことは、むしろ健全なメディアリテラシーの証です。

2025,江端さんの忘備録

殺人事件の被害者について、近所の人へのインタビューでは「明るくて、礼儀正しい人だった」というコメントが多いように思えます。
When neighbors are interviewed about a murder victim, they often say something like, “They were cheerful and well-mannered.”

しかし、もし私が殺人事件の被害者になったとして、誰かに「江端さんは明るくて、礼儀正しい人だった」と言われたら、私はきっと『デタラメ言うな!』と文句を言いたくなるでしょう。
However, if I were ever to become a murder victim and someone said, “Mr. Ebata was cheerful and well-mannered,” I’d probably want to shout, “Don’t talk nonsense!”

一方で、もし私が殺人事件の加害者になった場合、「明るくて、礼儀正しい人だったから、びっくりしました」とは言われないだろう、という点で、家族全員の意見が一致しています。
On the other hand, if I were to become the perpetrator of a murder, my entire family agreed that no one would say, “He was cheerful and well-mannered, so it was a real shock.”

むしろ、家族ですら、「父(または夫)なら、何をやらかすか分からない人でした」と言いかねません(ちなみに私はこの発言、O.Kと伝えてあります)。
Even my family might say, “As a father (or husband), he was the type you never knew what he’d do.” (Incidentally, I’ve given my approval for this comment.)

つまり私は、「殺されても同情されず、殺しても驚かれない」という、どっちに転んでも損なキャラクターに仕上がっていたようです。
In short, it seems I’ve ended up with a character profile where I wouldn’t get sympathy if I were killed, nor surprise if I did the killing—a raw deal either way.

あとは、以下のChatGPTの対応をご覧ください。
Now then, please proceed to the following ChatGPT response.

『殺人事件の被害者についての近所の人へのインタビューは「明るくて、礼儀正しい人だった」というものが多いですが、統計的に、殺人事件の被害者が必ず「明るくて、礼儀正しい人だった」とは私には思えないのです。これはいわゆる偏向報道ではないでしょうか』とChatGPTに質問してみた件

未分類

最終審査は"final defense"と言われているようです。審査が"defense"と言われるのに違和感があります。

はい、ごもっともな違和感です。しかし、アカデミックな英語圏では「審査(とくに博士論文の口頭審査)」を “defense(防衛)” と呼ぶのはごく一般的な慣習です。以下にその背景を説明します。


■ なぜ “defense” と呼ぶのか?

“defense” とは、**「自分の研究を審査員の質問や批判から論理的に守ること」**を意味しています。つまり、

博士号取得者にふさわしいかどうかを確認するための、知的な戦いの場

というイメージです。


■ 歴史的な背景(ラテン語起源)

この表現は、ヨーロッパ中世の大学でのラテン語に由来します。

  • “disputatio”(討論)

  • “defensio”(防衛)

博士候補者は、審査委員や他の学者たちの前で論文を公開し、質疑応答に応じて**自らの理論・データ・結論の正しさを「守る」**ことが求められました。この伝統がそのまま英語圏に引き継がれています。


■ defense = 「口頭試問」のニュアンス

“defense” は単なる「発表」ではなく、以下のような一連の行為を含みます:

  1. 自分の研究成果をプレゼンする(説明)

  2. 質問に答える(理解の深さを示す)

  3. 批判や反論に対応する(論理性・独創性を示す)

したがって、「審査」と訳すと少し機械的に見えますが、“defense” は、自己の知的立場を積極的に守り抜く行為と理解するのが妥当です。


■ 例文:

  • She is preparing for her PhD defense next month.
    (彼女は来月の博士論文審査の準備をしている)

  • The defense committee asked tough questions.
    (審査委員会は鋭い質問を投げかけた)


■ 違和感のまとめ:

「防衛(defense)」=「知の自己証明」
日本語の「審査」よりも、「論戦」「応答責任」「最終テスト」というニュアンスが強く、博士号授与の最終関門としての意味合いが込められています。


必要であれば「口頭試問(oral examination)」という言い方もありますが、特にアメリカの大学では “(final) defense” が正式かつ日常的に使われています。

2025,江端さんの技術メモ

以下に、Go言語で実装するシンプルな mTLS(相互TLS認証)通信プログラムを示します。
これは、サーバがクライアント証明書の検証を行い、クライアントがサーバに接続してデータを送るという最小構成のデモです。


✅ ファイル構成

.
├── server.go ← mTLS対応サーバ
├── client.go ← mTLS対応クライアント
├── ca.crt ← ルートCA証明書
├── server.crt ← サーバ証明書(caで署名)
├── server.key ← サーバ秘密鍵
├── client.crt ← クライアント証明書(caで署名)
└── client.key ← クライアント秘密鍵

🖥️ サーバ側(server.go

package main

import (
	"crypto/tls"
	"crypto/x509"
	"fmt"
	"io"
	"log"
	"net/http"
	"os"
)

func main() {
	// クライアント証明書を検証するためのCA証明書読み込み
	caCert, err := os.ReadFile("ca.crt")
	if err != nil {
		log.Fatal(err)
	}
	caPool := x509.NewCertPool()
	caPool.AppendCertsFromPEM(caCert)

	// TLS構成
	tlsConfig := &tls.Config{
		ClientAuth: tls.RequireAndVerifyClientCert,
		ClientCAs:  caPool,
		MinVersion: tls.VersionTLS12,
	}

	server := &http.Server{
		Addr:      ":8443",
		TLSConfig: tlsConfig,
	}

	http.HandleFunc("/secure", func(w http.ResponseWriter, r *http.Request) {
		fmt.Fprintln(w, "mTLS通信成功!")
	})

	log.Println("mTLSサーバ起動中:https://localhost:8443/secure")
	err = server.ListenAndServeTLS("server.crt", "server.key")
	if err != nil {
		log.Fatal(err)
	}
}

💻 クライアント側(client.go

package main

import (
	"crypto/tls"
	"crypto/x509"
	"fmt"
	"io"
	"log"
	"net/http"
	"os"
)

func main() {
	// クライアント証明書と鍵の読み込み
	cert, err := tls.LoadX509KeyPair("client.crt", "client.key")
	if err != nil {
		log.Fatal(err)
	}

	// サーバ証明書を検証するためのCA証明書読み込み
	caCert, err := os.ReadFile("ca.crt")
	if err != nil {
		log.Fatal(err)
	}
	caPool := x509.NewCertPool()
	caPool.AppendCertsFromPEM(caCert)

	// TLS設定
	tlsConfig := &tls.Config{
		Certificates:       []tls.Certificate{cert},
		RootCAs:            caPool,
		InsecureSkipVerify: false,
	}

	client := &http.Client{
		Transport: &http.Transport{TLSClientConfig: tlsConfig},
	}

	// サーバにリクエスト
	resp, err := client.Get("https://localhost:8443/secure")
	if err != nil {
		log.Fatal(err)
	}
	defer resp.Body.Close()

	body, _ := io.ReadAll(resp.Body)
	fmt.Printf("サーバ応答: %s\n", string(body))
}

🔐 証明書の作成(OpenSSL例)

# CA作成
openssl genrsa -out ca.key 2048
openssl req -x509 -new -nodes -key ca.key -subj "/CN=TestCA" -days 3650 -out ca.crt

# サーバ証明書
openssl genrsa -out server.key 2048
openssl req -new -key server.key -subj "/CN=localhost" -out server.csr
openssl x509 -req -in server.csr -CA ca.crt -CAkey ca.key -CAcreateserial -out server.crt -days 3650

# クライアント証明書
openssl genrsa -out client.key 2048
openssl req -new -key client.key -subj "/CN=myclient" -out client.csr
openssl x509 -req -in client.csr -CA ca.crt -CAkey ca.key -CAcreateserial -out client.crt -days 3650

✅ 実行方法

  1. 上記のOpenSSLコマンドで証明書類を生成
  2. server.go を起動

  3. client.go を別ターミナルで起動

以下のエラーが発生

ebata@DESKTOP-1QS7OI7:~/test_tls$ go run client.go
2025/07/29 02:33:59 Get "https://localhost:8443/secure": tls: failed to verify certificate: x509: certificate relies on legacy Common Name field, use SANs instead

x509: certificate relies on legacy Common Name field, use SANs instead
→ Go の TLS ライブラリ(特に Go 1.15 以降)では、Common Name(CN)だけの証明書ではサーバ認証に失敗します。
現在は SAN(Subject Alternative Name) が必要です。


✅ 対応策:証明書を SAN を含めて再生成する

OpenSSL の設定を使って、SAN付き証明書を発行します。


🔧 手順(openssl

1. san.cnf という設定ファイルを作成:

# san.cnf
[req]
default_bits       = 2048
distinguished_name = req_distinguished_name
req_extensions     = req_ext
prompt             = no

[req_distinguished_name]
CN = localhost

[req_ext]
subjectAltName = @alt_names

[alt_names]
DNS.1 = localhost

2. サーバ証明書を SAN付きで再生成:

# サーバ鍵生成
openssl genrsa -out server.key 2048

# CSR作成
openssl req -new -key server.key -out server.csr -config san.cnf

# 証明書発行(CAで署名)
openssl x509 -req -in server.csr -CA ca.crt -CAkey ca.key -CAcreateserial \
  -out server.crt -days 3650 -extensions req_ext -extfile san.cnf

✅ 説明

項目 内容
CN Common Name。旧来のFQDN指定(非推奨)
SAN Subject Alternative Name。現在はこちらが必須
localhost クライアントから接続するホスト名と一致させる必要あり

GoはこのSANにlocalhostが含まれていないとTLS検証に失敗します。


✅ 再実行の流れ(修正後)

go run server.go
# → 起動確認「mTLSサーバ起動中:https://localhost:8443/secure」

go run client.go
# → サーバ応答: mTLS通信成功!