2026,江端さんの忘備録

昨日、ChatGPTと今回の衆議院選挙について話をしていたのですが、2つほどインパクトのある話をされました。
Yesterday, I was talking with ChatGPT about the recent House of Representatives election, and it presented me with two particularly striking points.

1つ目が「『チームみらい』の躍進」の話でした。
The first was about the surge of “Team Mirai.”

ここの話で、はじめて「エンジニア票」という新概念がChatGPTによって提唱されました。
In this context, ChatGPT introduced a new concept: the “engineer vote.”

私たちエンジニアから見ると、政治というのは、まったくもって不合理な意思決定システムで運用されており、その非効率性は、目を覆うばかりです。
From the perspective of engineers, politics operates as an utterly irrational decision-making system, and its inefficiency is frankly staggering.

もっとも、これは、エンジニアリングが対象とする評価軸(KPI)が明確であるからとも言えます。
That said, this perception likely stems from the fact that engineering deals with clearly defined evaluation axes (KPIs).

---

これを具体的に言うと、例えば次のような違いです。
To put this more concretely, consider the following differences.

エンジニアリングの世界では、処理速度を上げたいのか、コストを下げたいのか、信頼性を高めたいのか、障害発生率を下げたいのか、といった目的が事前に定義され、それぞれがKPIとして数値化されます。
In engineering, objectives such as increasing processing speed, reducing costs, improving reliability, or lowering failure rates are defined in advance and quantified as KPIs.

そのKPIに対して、設計変更や実装変更が「改善か、改悪か」は、原則として測定結果で判断されます。
Whether a design or implementation change constitutes an improvement or a deterioration is, in principle, judged by comparing measured results against the KPIs.

ところが政治の世界では、経済成長、国民の安心、公平性、国際的な立場、といった抽象度の高い目標が並ぶ一方で、それらがどの指標で、どの時点で、どの程度達成されたのかが明確に示されることは、ほとんどありません。
In contrast, the political world is filled with highly abstract goals, such as economic growth, public security, fairness, and international standing. Yet, it is rarely made clear by what indicators, at what point in time, and to what extent these goals have been achieved.

エンジニアの感覚からすれば、「目的関数が定義されていない最適化問題」、あるいは「評価関数が状況によって毎回書き換えられるシステム」を延々と運用しているように見えるのです。
To an engineer, it appears to involve repeatedly solving an optimization problem with no defined objective function, or a system whose evaluation function is rewritten each time, depending on circumstances.

---

では、エンジニア層に「チームみらい」の何が刺さったのか?
What, specifically, resonated with the engineering community about “Team Mirai”?

最大の理由は、彼らの主張や語り口が、「正しさ」や「理想」を前面に押し出すものではなく、仕組みと運用の話として政治を語っていた点にあります。
The main reason lies in the fact that their arguments and rhetoric did not foreground “correctness” or “ideals,” but instead framed politics in terms of mechanisms and operations.

多くの政党は、「こうあるべきだ」「こうしたい」「国民のために」という“目的”の宣言から話を始めます。
Many political parties begin by declaring their “objectives,” such as “this is how things should be,” “this is what we want to do,” or “for the sake of the people.”

しかし、エンジニアがまず知りたいのは、「それはどう実装されるのか」「失敗した場合、どうロールバックするのか」「どこを観測して、何をもって成功・失敗と判断するのか」です。
Engineers, however, first want to know: how it will be implemented, how it will be rolled back if it fails, what will be observed, and by what criteria success or failure will be judged.

『チームみらい』のメッセージには、
The messages of “Team Mirai” included the following assumptions:

・制度は一度作ったら終わりではなく、改善し続ける対象である
・現場のデータや実態を見ながら設計を更新する
・万能解は存在せず、試行錯誤を前提とする
Those systems do not end once created but are subject to continuous improvement.
that designs should be updated while observing on-site data and realities;
and that no universal solution exists, making trial and error a given.

という、エンジニアにとって極めて馴染み深い――というか、当たり前の前提が、最初から組み込まれていました。
These extremely familiar, indeed, obvious premises for engineers were built in from the outset.

これは言い換えれば、「政治を完成形の理想像として語らなかった」ということです。
In other words, they did not talk about politics as a finished, idealized form.

エンジニアは、完成されたシステムよりも、「今どこが壊れているのか」「どこに技術的負債が溜まっているのか」「どこから手を付ければ改善余地があるのか」を説明される方が、よほど納得します。
Engineers are far more convinced by explanations of where systems are currently broken, where technical debt has accumulated, and where improvements can begin, than by claims of a perfectly finished system.

政治の世界ではしばしば、「理想を掲げること」そのものが評価されますが、エンジニアの世界では、「現状を正確に把握し、制約条件込みで語ること」の方が圧倒的に信頼されます。
In politics, simply proclaiming ideals is often valued in itself. In the engineering world, however, accurately grasping the current situation and speaking with constraints fully acknowledged commands far greater trust.

『チームみらい』が示したのは、「正解を持っている集団」ではなく、「まだ未完成だが、改善する意思と方法論を持っている集団」という姿でした。
What “Team Mirai” presented was not a group claiming to have the correct answers, but one that was still unfinished yet possessed the will and methodology to improve.

そしてそれは、不完全なシステムを前にしても、「直せる」「直し方が分かる」「一緒に直せる」と信じて日々仕事をしているエンジニアにとって、極めて「理解可能な言語」で書かれた政治の姿を見せたからです。
For engineers who work every day, believing that imperfect systems can be fixed, knowing how to fix them, and fixing them together, this was a form of politics written in an eminently understandable language.

実は、これ、別段新しい概念ではなく、EBPM(Evidence-Based Policy Making)の一態様です。
In fact, this is not a particularly new concept; it is a form of EBPM (Evidence-Based Policy Making).

政策を理念や印象論ではなく、データや実証結果(エビデンス)に基づいて立案・評価・改善していこうとする考え方ですが、既存政党は、これを理解していなかったか、あるいは理解していてもやっていなかったか、あるいは選挙で、EBPMを真面目に訴えなかったのです。
EBPM seeks to formulate, evaluate, and improve policies based on data and empirical evidence rather than ideology or impressions, yet existing parties either did not understand this, did not practice it even when they did, or failed to advocate it seriously during elections.

で、私が思うに、「チームみらい」は、これを、初めて政党として主張した――これが、いわゆるエンジニア層の票を拾ったのだと考えられます。
In my view, “Team Mirai” was the first party to explicitly assert this approach, which captured the votes of the engineering demographic.

――と、いうことを、ChatGPTに教えて貰いました。
That, at least, is what ChatGPT told me.

---

私は、日本のエンジニア人口を1000万人程度(*)と見ています。
I estimate the number of engineers in Japan to be around ten million(*).

(*)「典型的に技術者と呼べる層」として、職業分類の「技術者」は、男性329万人+女性56万人で、合計約385万人と見ています。次に、施工・工事寄りの職種として「建設・採掘従事者」が約275万人います。さらに、製造現場の「生産工程従事者」が約864万人いますが、ここは「全員が技術者」というわけではありません。そのため、保全、段取り、調整、検査、修理などを含む「技術に関わる業務」の比率を3割と仮定すると、約260万人程度になります。以上を合計すると、私は日本のエンジニア人口をおおよそ920万人、すなわち約1000万人規模と見ています。
(*)As a group typically described as engineers, I estimate that the occupational category “engineers” comprises approximately 3.85 million people in total: 3.29 million men and 0.56 million women. Next, approximately 2.75 million people are classified as “construction and mining workers,” which includes occupations more closely associated with on-site construction and engineering work. In addition, there are approximately 8.64 million “production process workers” in manufacturing, but this group cannot be regarded as consisting entirely of engineers. Therefore, if we assume that about 30 percent of this group is engaged in technology-related tasks such as maintenance, setup, coordination, inspection, and repair, that yields roughly 2.6 million people. Adding these figures, I estimate the population of engineers in Japan to be approximately 9.2 million, on the order of 10 million.

この1000万人全員が、エンジニアリング思考をするとは限りませんが、「政治やっている奴って、本当にバカじゃねーの」と思っているエンジニアは、そこそこの人数いるとは思うんですよ。
Not all of these ten million think in engineering terms, but I do believe there are quite a few engineers who think, “Aren’t the people running politics seriously stupid?”

これから、『チームみらい』が政治の表舞台にでてくるか、あるいは、他の政党がこのエンジニアリング思考を取り込んでいくのかは不明ですが――いずれにしても、今回の『チームみらい』の功績は大きいと思います。
Whether “Team Mirai” will move to the center of the political stage or other parties will incorporate this engineering mindset remains unclear; in any case, I believe their contribution this time was significant.

---

2つ目が「SNSのバックエンドとしての生成AIの登場」でした。
The second point concerned the emergence of generative AI as the backend of social media.

今や、SNSにおける情報を、そのまま真に受ける人間はおらず、その前にファクトチェックをするようになっているようです。
These days, few people accept information on social media at face value; people tend to fact-check it first.

で、そのファクトチェックは、SNSの過激な意見や真偽が不明な主張のチェックだけではなく、
And that fact-checking is not limited to verifying extreme opinions or dubious claims on social media.

―― こう考えてしまう自分はズレていないか
Am I off base for thinking this way?

という、セルフチェックによって、自分の主張の妥当性を検証する為にChatGPTが使われていると、ChatGPT自身が言っていました。
ChatGPT stated that it is also used for self-checking to verify the validity of one’s own views.

この理由が凄い。
The reasoning behind this is striking.

- 正解がない
- しかし棄権もできない
- しかも、結果の重さだけは分かっている
There is no correct answer.
Yet abstention is not an option;
And only the gravity of the outcome is clear.

この状況で人が欲しくなるのは、『結論ではなく、(自分の)思考の妥当性の確認』というものです。
In such a situation, what people want is not a conclusion, but confirmation of the soundness of their own thinking.

専門家、評論家、SNSは、もはや信頼するソースとは見なされず、“ノイズ”のレベルに堕ちてしまい、せいぜい「生成AIと一緒に考えるための“ネタ”程度の取り扱いになっている」ということのようです。
Experts, commentators, and social media are no longer regarded as reliable sources, having fallen to the level of “noise,” at best treated as material to think through together with generative AI.

今や『誰かに“決めてもらう”ことへの不信が、かなり深いところまで進んだ』と言えます。
It can now be said that distrust of having someone else “decide for you” has reached a deep level.

で、「自分の判断を他人に預けたくない」が、「しかし完全な独断にも耐えられない」という人が、
As a result, people who do not want to entrust their judgment to others, yet cannot endure complete self-reliance,

―― 生成AIを、自分の思考の『壁打ち』として使うようになった
have come to use generative AI as a “sounding board” for their own thinking.

---

つまるところ、選挙におけるSNS戦略なんぞ、すでに時代遅れになっているということです。
In short, social-media-based election strategies are already outdated.

SNSはあくまでトリガーとしてのフロントエンド(GUI程度の役割)であって、意思決定システムは、ChatGPTのような生成AIに移行しているのです。
Social media merely serves as a trigger-like front end (akin to a GUI), while the actual decision-making system has shifted to generative AI such as ChatGPT.

という訳で、テレビの解説などで、未だに「SNSによる選挙投票の危険性」とか言っている、テレビのコメンテータや専門家を見ていると「こいつら、アホだなぁ」と思ってしまうわけですよ――そんなフェーズ、すでにエンドロールに入っているのに。
That is why, when I see TV commentators and experts still talking about the “dangers of SNS-driven voting,” I can’t help thinking, “These people are idiots, that phase has already rolled into the end credits.

---

そして、生成AIが仕切る選挙は、SNSよりも怖い――なにしろ、論理的な風を装って分かりやすい言葉で、筋の通った話を、誠実にしてくるからこそ「怖い」。
Elections mediated by generative AI are even more frightening than those driven by social media precisely because they present coherent arguments in clear language, under the guise of logic and sincerity.

私は、ChatGPTの言うことを素直に信じません。主張の矛盾点を突いて、ChatGPTにちゃんと謝罪までさせています――でも、ここまでやっている人って、どれくらいいるんでしょうか?
I do not take ChatGPT's output at face value. I point out contradictions in its claims and even make it apologize, but how many people go that far?

生成AIの言うことを、まるっきり信じてはダメです。
You must never believe what generative AI says wholesale.

必要に応じて、矛盾や論理矛盾を指摘して、ちゃんと喧嘩をしないと、健全な生成AIを育てることができません。
If necessary, you have to point out contradictions and logical inconsistencies and properly “argue” with them; otherwise, you cannot cultivate a healthy relationship with generative AI.

権力が、これから生成AIを抱き込みにかかるのは予定調和です――私が権力側であれば、必ず“ここ”を調略します。
It is almost predetermined that those in power will try to co-opt generative AI. If I were on the side of power, I would certainly target this point.

未来のAI社会を健全にする為には、生成AIに対して、ちゃんと対峙する知性と気合が必要です。
To keep a future AI-driven society healthy, we need the intelligence and resolve to confront generative AI head-on.

『私達は生成AIごときに支配されるほど、愚かではない』ということを、がっつり示していきましょう。
Let us firmly demonstrate that we are not so foolish as to be ruled by something like generative AI.

『昨日の選挙結果を踏まえて、参政党が15議席、日本保守党が0議席となり、結果がかなり変わりました。両方とも外国人問題については同じ方向のように見えましたが、何がこの結果を左右したのでしょうか』とChatGPTと話をしてみた件

2026,江端さんの忘備録

今回、自民党の歴史的大勝利――というより、中道改革連合を含めた野党の歴史的大敗と言えると思います。
This time’s result can be described as a historic landslide victory for the Liberal Democratic Party—or rather, a historic defeat for the opposition parties, including the centrist reform coalition.

まあ、トップの辞任は仕方がないと思いますし、「(自分の責任は)万死に値する」という反省の念も大切かとは思います。
Of course, I think the resignation of the party leader is inevitable, and expressions of remorse such as “my responsibility deserves ten thousand deaths” also have their place.

とは、思いますが――どうせなら、
That said—if we’re going to go that far—

―― お前らバカなのか! このまま、国家をこの方向にしていっていいのか! 国民全員死ね!!
“Are you all idiots? Is it really okay to take the country in this direction? Drop dead, every last one of you!!”

というような捨てゼリフを吐いて、政界から引退しても、「それはそれでありかな」とも思うんですよね。
If someone were to spit out a parting shot like that and then retire from politics, I might even think, “Well, that’s one way to do it.”

(私なら、やるぞ)
(If it were me, I’d do it.)

---

とは言え、選挙というシステムは、「そっかー、みんながそう考えるなら、私も考え方を変えていかなくちゃなぁ」という、自分の思想の自己点検をする機会でもあります。
That said, elections are also a system that allows us to self-check our own beliefs—to think, “I see, if this is what everyone thinks, maybe I need to reconsider my own views.”

私、今回の選挙結果だけでなく、外国人排斥(とは言わないのかもしれませんが)や、古くは憲法改正支持者の数にも――頭を殴られるようなショックを受けたのを覚えています。
I remember feeling as if I’d been hit over the head, not only by the outcome of this election, but also by attitudes toward excluding foreigners (though that may not be the right term), and even earlier by the sheer number of people supporting constitutional revision.

―― 私の考え方は、マジョリティとは乖離している(あるいは「時代遅れ」)
—That my way of thinking is out of step with the majority (or perhaps “outdated”)

という事実を目の前に突きつけられるのは、正直つらいことではありますが、それでも、「これが多数派の意思なのだ」と力づくで理解させられることは、自分の考え方を変える力にはなると思います。
Being forced to confront that fact head-on is honestly painful, but even so, being compelled to accept that “this is the will of the majority” can become a force that changes one’s own thinking.

---

そんな中であっても、「我が国の国民が、『選挙の運用』に対してだけは絶対的に信頼している」という点は、誇れることだなあ、と思うんですよ。
Even so, I think we can be proud of the fact that the people of this country have absolute trust—at least—when it comes to the administration of elections.

どこぞの国の大統領のように、自分の都合の悪い選挙結果に対して「票が盗まれた」などと言い出す人間が、だたの一人もいないことは――なんと素晴らしいことか、と、この一点において“のみ”、私は、自分の国を誇ることができるのです。
The fact that there is not a single person here who, like some foreign president, claims “the votes were stolen” when faced with an unfavorable result—how wonderful that is. On this one point alone, I can genuinely feel proud of my country.

なんで、日本においては、このような「不正投票」という概念がほとんど出てこないのか、不思議です。
I find it fascinating that, in Japan, the concept of “election fraud” rarely arises.

---

日本の選挙は、良くも悪くもアナログの塊です。
Japanese elections are, for better or worse, a mass of analog processes.

・紙の投票用紙
・手作業での開票
・開票所に立会人・報道・候補者陣営が同席
・開票速報が「開票率0%でも当確」という形で出る(=出口調査・情勢分析が主)

* Paper ballots
* Manual vote counting
* Witnesses, media, and candidate representatives present at counting stations
* Early results declaring winners even at “0% counted” (based mainly on exit polls and situation analysis)

この構造では、「どこかで大量に票を書き換えた」という物語を作るのが極めて難しいです。機械集計や電子投票のような「ブラックボックス」がほぼ存在しないため、疑念が入り込む余地が制度的に小さいわけです。
Under this structure, it is extremely difficult to construct a story about “mass vote tampering somewhere.” Because there are almost no black boxes like machine counting or electronic voting, the institutional space for suspicion to creep in is very small.

---

また、選挙の運用が「政治から切り離されている」という点も見逃せません。
Another important point is that the administration of elections is separated from politics.

日本では、選挙管理委員会が地方自治体に常設されており、与野党どちらの政権下でも基本的な運用は変わりません。ここで重要なのは、「信用している」のではなく、「疑っても崩れない構造」になっている点です。
In Japan, election management committees are permanently established within local governments, and basic operations do not change regardless of whether the ruling party or the opposition is in power. The key point here is not that we “trust” the system, but that it is built to withstand scrutiny, even when questioned.

仮に負けた側が「不正だ!」と叫んだ場合でも、
Even if the losing side were to shout “fraud!”,

・具体的にどこで
・誰が
・どうやって
・何票分

* where exactly
* Who did it
* how it was done
* and for how many votes

をやったのかを、裁判で立証しなければなりません。このハードルの高さが、陰謀論の流通を事前に抑え込んでいます。
They would have to prove all of that in court. This high hurdle suppresses conspiracy theories before they can spread.

---

加えて、我が国には「負けを受け入れる」文化があります。これ、かなり異質な政治文化です。
In addition, our country has a culture of “accepting defeat.” This is a fairly unusual political culture.

先に書いた「自分の思想の自己点検をする機会」という感覚が、政治家側にも、有権者側にも、ある程度共有されているからです。
That’s because the sense of elections as an opportunity to re-examine one’s own beliefs is shared, to some extent, by both politicians and voters.

これは民主主義としては非常に成熟した振る舞いで、世界的に見れば、むしろ例外的です(驚異的に例外)。
This is an extremely mature behavior for a democracy, and globally speaking, it is actually exceptional—astonishingly so.

---

さらに、負けた側が「不正だ」と言っても支持は増えず、むしろ「見苦しい」「往生際が悪い」で終わり、次の選挙に不利になるという事実があり、「不正投票論」は、政治的に見てコストパフォーマンスは最悪です。
Moreover, when the losing side claims “fraud,” it does not gain support; instead, it is seen as “undignified” or “a bad loser,” which hurts them in the next election. From a political standpoint, fraud narratives have the worst possible cost-performance ratio.

比して、アメリカ合衆国では、「負け=不正の可能性を最後まで主張する」ことが、支持者動員の戦略として成立してしまいました。その象徴が、ドナルド・トランプによる「盗まれた選挙」という物語です――で、まあ、日本では、非常に不快なものとして見えてしまう、と。
By contrast, in the United States, insisting on the possibility of fraud until the very end has come to function as a supporter-mobilization strategy. The symbol of this is Donald Trump’s “stolen election” narrative—and from Japan, it simply looks extremely unpleasant.

---

我が国は、総じて「政治不信」は腐るほどあるのですが、「選挙不信」はない。
In our country, there is an abundance of distrust in politics, but none in elections.

本当にない。限りなく0%です。
There truly isn’t any—it's practically zero percent.

これは民主主義社会における一種の「奇跡」と言ってもいいと思うんですよね。
I think it’s fair to call this a kind of “miracle” in a democratic society.

---

私、「日本バンザイ型コンテンツ」をいつも不快な思いで見てしまうのですが、
I usually watch “Japan-is-great” type content with a sense of discomfort, but

我が国が「『選挙不信』ゼロの国」という点においては、
when it comes to the fact that our country is a nation with “zero election distrust,”

ラウドスピーカーを10台積んで、街中を走り回っていいくらい「自慢していいことだ」と思っているのです。
I think it’s something we can brag about—so much so that we could mount ten loudspeakers on a truck and drive around town shouting about it.

『昨日の選挙結果を踏まえて、参政党が15議席、日本保守党が0議席となり、結果がかなり変わりました。両方とも外国人問題については同じ方向のように見えましたが、何がこの結果を左右したのでしょうか』とChatGPTと話をしてみた件

2026,江端さんの忘備録

現在、私が連載している「リタイア直前エンジニアの社会人大学漂流記」では、実際の大学名や学部名、お世話になった先生方の名前をすべて記載する、という方針で執筆しております。
In my ongoing series “A Near-Retirement Engineer’s Drift Through University as a Working Adult,” I write under the policy of fully disclosing the actual names of the universities, faculties, and professors who have supported me.

「某大学」の「某先生」では、どうにもリアル感が出ないからです。
Referring only to “a certain university” or “a certain professor” fails to convey any sense of reality.

それゆえ、私が博士課程でお世話になった先生方全員(4名)に原稿チェックをお願いしておりますし、大学名も明記しておりますので、大学の広報担当者の方にも確認をしていただいております。
For that reason, I ask all four professors who supervised me during my doctoral studies to review the manuscript, and since the university name is explicitly stated, I also have it checked by the university’s public relations office.

『記述に問題があれば無条件で修正し、必要であれば原稿全体をボツにする』
“If there are any problems in the wording, I will revise it unconditionally, and if necessary, discard the entire manuscript.”

と、約束しております。
That is the promise I have made.

私は、真実を追い求めるジャーナリストでもなければ、何かを告発する使命を帯びた書き手でもありません。単に、雑文を書くエンジニアのコラムライターに過ぎません。
I am neither a journalist in pursuit of truth nor a writer on a mission to expose something. I am simply an engineer who writes casual columns.

お世話になった先生方や大学当局の方々のご気分を害してまで、書きたいことなどありません。
I have no intention of writing anything that would offend the professors who helped me or the university authorities.

現在、日本の大学のキャンパスは、学期末を終えて閑散としている――と思いきや、卒業論文の提出や修士論文の発表など、卒業のかかった学生さんたちにとっては、まさに熱い闘いの最中のようです。
At present, university campuses in Japan may appear quiet after the end of the semester—yet for students whose graduation is on the line, with bachelor’s theses due and master’s theses to defend, it is very much the middle of an intense battle.

当然、指導にあたる先生方の忙しさも、相当なものではないかと思います。
Naturally, I imagine that the professors supervising them are also extremely busy.

そんな中で、その忙しい先生方に、私のコラム原稿にまで目を通していただくことには、大変申し訳ない気持ちになります。
Under such circumstances, I feel genuinely apologetic for asking those busy professors to take the time to read even my column manuscript.

---

私自身、学生時代(社会人大学生ではない頃)を振り返ってみますと、確かに忙しかった記憶はあります。
When I look back on my own student days (before I became a working adult student), I do remember being busy.

ただ、その忙しさの「質」は、今とはかなり違っていたように思います。
However, the “quality” of that busyness feels quite different from what it is now.

――自分がやっている研究は自分だけのものであり、他人(教授)からとやかく言われるものではない
—The research I am doing is mine alone, and not something others (professors) should interfere with.

そんな、今となっては夢のようなことを信じていられたあの頃は、ある意味で幸せだったのだと思います。
Believing something so dreamlike, in hindsight, probably meant that I was happy in a certain sense.

ただ、常に何かに腹を立てていた記憶もありますので、QOLは決して高くはなかった気もしますが。
That said, I also remember being angry most of the time, so my quality of life was likely low.

現在では、研究は「命じられるもの」であり、その命じられた範囲の中で、自分が「良いと思うやり方」をどこまで使えるか、という話になっています。
Today, research is something that is “assigned,” and the question becomes how much freedom one can exercise within the assigned scope to use methods one believes are good.

企業研究とは、そういうものですし、そうでなければ企業の研究ではありません。
That is what corporate research is, and if it were otherwise, it would not be corporate research.

また、研究内容に対して「こういう成果を出せ」という明示的、あるいは暗示的な示唆が与えられる点も、学生時代との大きな違いです。
Another significant difference from my student days is that explicit or implicit instructions are given about what kind of results should be produced.

研究というものは、本来「やってみて、その結果を示す」だけのものであるはずですから、自分や組織の予想通りにならないことなど、珍しくもありません。
Research, by its nature, should involve trying something and presenting the results, so outcomes that differ from one’s own or the organization’s expectations are not unusual.

しかし、その「普通」が封じられているという点が、学生時代の研究との決定的な違いだと感じています。
Yet the fact that this “normal” state of affairs is suppressed is, to me, the decisive difference from research in my student days.

定期的にチェックを受け、予想通りの結果が出ないと、予想通りの結果が出るような助言(という形の業務命令)を受け、それでも結果が出なければ、研究原資が止められることになります。
One is periodically reviewed, and if the results are not as expected, one receives advice—effectively work orders—to steer the results in the expected direction; if that still fails, the research funding is cut off.

もちろん、仕事として研究を行っている以上、それは当然と言えば当然なのですが、一つ言えることは、「自分がやっている研究は自分だけのもの」という考えとは、完全に無縁の世界だということです。
Of course, since this is research done as part of one’s job, this may be inevitable, but one thing is clear: it is a world completely detached from the idea that “the research I am doing is mine alone.”

――自分には1mmも興味がなく、「どうなろうが知ったことか」と思ってしまうようなテーマであっても、一定の成果(に見えるもの)を出さなければならない
—Even on topics that do not interest me in the slightest, and about which I might think “whatever happens is none of my concern,” I still have to produce a certain level of results—or at least something that looks like results.

そうした日々は、正直なところ、なかなかに辛いものです。
Days like that can be pretty painful.

---

そうした中で、「社会人大学生」という立ち位置は、実に微妙なものだと感じています。
In this context, the position of being a “working adult student” feels extremely delicate.

会社から学費援助を受けている以上、会社に利益をもたらす研究から完全に逃れることはできませんが、週末や休日に行う私的な研究に対して、露骨な干渉を受けることはありません。
As long as I receive tuition support from my company, I cannot entirely avoid research that benefits the company. Yet, I am not subjected to overt interference in the private research I do on weekends or holidays.

一方で、論文発表などについては社内の稟議を通さなければならず、その手続きそのものに加え、その説明にも膨大なコスト(時間)がかかります。
On the other hand, publishing papers requires going through internal approval processes, and explaining them demands a substantial time cost.

自分の裁量で研究を進めている分、その説明の面倒くささは、決して小さくありません。
Because I conduct the research at my own discretion, explaining it is far from trivial.

さらに、会社には博士号取得者が多数おりますので、必然的に「一言ある」「クセのある」人間ばかりになります。
Moreover, since there are many PhD holders in the company, it inevitably becomes a place full of people who “always have something to say” and have strong individual quirks.

下手をすると、大学の指導教員に説明するよりも、はるかに骨が折れることもあります。
At times, it can be far more exhausting than explaining things to my university supervisor.

---

そんな中、先日、研究の指導をしてくださった先生から、「社会人大学生は、根回しが実に上手い」というお話を伺いました。
Amid all this, I recently heard from a professor who supervises my research that “working adult students are remarkably good at groundwork.”

「会社(というか社会)は、根回しで決まる」という現実を骨の髄まで知り尽くしている社会人大学生は、審査の前に審査官の先生方のもとに足を運び、説明を重ね、ご納得いただける方向に研究成果を調整していく――そうした腹芸に対して、ほとんど躊躇がありません。
Working adult students, who understand, down to their bones, the reality that “companies—or rather society—run on groundwork,” have little hesitation in visiting examiners before evaluations, repeatedly explaining their work and adjusting the results to outcomes that will gain approval.

――「自分の信念」よりも「最小効率で通す」が正義
—Justice lies not in “one’s own convictions,” but in “getting it through with minimal effort.”

その現実を知り尽くしている私たち社会人は、20年程度の時間を「金(利益・収益)」という概念の外側で生きることができた学生さんたちとは、踏んできた修羅場の数が違います。
We working adults, who know this reality all too well, have faced a very different number of ordeals compared with students who were able to spend some twenty years living outside the concept of money, profit, and revenue.

---

こうして振り返ってみますと、私がこのコラムで実名を記し、先生方や大学当局に原稿チェックをお願いしている理由も、だんだんと見えてくる気がします。
Looking back in this way, I begin to see more clearly why I write real names in this column and ask professors and university authorities to review the manuscript.

それは、「リアルを伝えたいから」という格好の良い理由ではなく「通す」ためです。
It is not because I want to “convey reality” in some noble sense, but because I want to get it approved.

学生時代に信じていた「研究は自分のもの」という牧歌的な幻想は、企業研究の現場で叩き潰され、「信念よりも、最小コストが正義」という社会の現実を、骨身に染みて学びました。
The pastoral illusion I held as a student—that research is one’s own—was crushed in the world of corporate research, where I learned painfully that in society, minimal cost often outweighs personal conviction.

同様に、この雑文コラムもまた、独りよがりな正義で突っ走る理由はありません。
If that is the case, there is no reason for this rambling column to charge ahead guided by self-righteous notions of justice.

「名前を出す」、「事前に見せる」、「問題があれば直す」、「必要であればボツにする」
Name names. Show it in advance. Fix problems if there are any. Discard it if necessary.

これは、言論の自由を自ら縛る行為ではなく、社会人大学生が身につけた、最も実用的な研究スキル――根回しの応用問題に過ぎません。
This is not an act of self-imposed restraint on freedom of expression, but merely an applied exercise of the most practical research skill that working adult students acquire: groundwork.

私は、真実を暴く記者でもなければ、学問の自由を体現する闘士でもありません。
I am neither a reporter who exposes truths nor a warrior embodying academic freedom.

単に、波風を立てず、関係者を不快にさせないことと、締切を同時に気にしながら原稿を書く――その辺に転がっている、普通のエンジニアの一人です。
I am simply an ordinary engineer, one of many, who writes while simultaneously worrying about deadlines and avoiding unnecessary conflict or discomfort among those involved.

そして多分、それこそが、いちばん「社会人大学生らしい」姿なのだろうな、と思いつつ、今日もメールの件名に「【ご確認のお願い】」と書いて、そっと送信するのです。
And perhaps that, I think, is the most “working adult student–like” of all, as I once again quietly send an email today with the subject line, “Request for Confirmation.”

「江端ファイアウォール」とは

2026,江端さんの忘備録

PCのディスクのバックアップをどんなに周到に行っておいたとしても、いきなり、新しいPCでアプリケーションが動き出す訳ではない ーー ということは、あまり知られていないのかもしれません。
No matter how carefully you back up a PC’s disk, applications do not suddenly start working on a new PC as they did before—this fact may not be widely recognized.

多くの人は、「バックアップさえ取っておけば安心」と思っています。
Many people believe that as long as they have a backup, they are safe.

写真や文書、仕事のファイルを丸ごと保存しておけば、万一パソコンが壊れても、新しいパソコンに移せば、前と同じように使えるはずだ、と。
They assume that if they save all their photos, documents, and work files, they can transfer them to a new PC and continue using them as before, even if the original PC fails.

これはごく自然な感覚です。
This is a perfectly natural way of thinking.

しかし実際には、バックアップは「データ」を守ってくれるだけで、「使える状態」まで自動的に連れてきてくれるわけではありません。
In reality, backups only protect “data”; they do not automatically bring back a usable working environment.

たとえるなら、引っ越しの際に家具や荷物はすべて運び込まれたものの、電気・ガス・水道がまだ開通しておらず、家電の置き場所も決まっていない状態に近いでしょう。
It is similar to moving house: all the furniture and belongings have been delivered, but electricity, gas, and water are not yet connected, and even the placement of appliances has not been decided.

アプリケーションは、単体で存在しているように見えて、実はその背後で多くの前提条件に支えられています。
Applications may appear to exist independently, but in reality, they rely on many underlying prerequisites.

パソコンの機種、OSの状態、内部設定、周辺機器との相性などが、長い時間をかけて「そのPC専用の環境」として形成されています。
The PC model, the state of the operating system, internal settings, and compatibility with peripheral devices gradually form an environment unique to that particular PC over time.

これを別のPCにそっくり移そうとしても、目に見えない部分が噛み合わず、うまく動かないことは珍しくありません。
When trying to transfer this environment wholesale to another PC, mismatches in invisible areas often prevent things from working correctly.

---

PCというのは、例えるなら「地層」のようなものです。
A PC can be compared to a geological layer.

その地層は、利用者が無意識のうちに積み重ねてきたものであり、その地層の上でしか成立しない建築物が、いわゆるアプリケーションです。
That layer is built up unconsciously by the user over time, and applications are structures that can only stand on top of that specific layer.

つまり、まっさらなPCで、これまで使ってきたアプリケーションをそのまま使うことは ーー 実務的には、ほぼ絶望的と言って差し支えないでしょう。
In other words, using the same applications exactly as they were on a brand-new PC is, in practical terms, almost hopeless.

だからといって、「諦めました」と言えないのが、私たちエンジニアです。
That said, engineers are not in a position to say, “I give up.”

この週末も、ある行政系アプリの導入をきっかけに、事実上使用不能となったPCから、別のPCへ環境を移行するために四苦八苦しています。この恨み、忘れるつもりはありません。
This weekend as well, I am struggling to migrate an environment from a PC rendered practically unusable by the introduction of a specific government-related application to another PC, and I have no intention of forgetting this resentment.

法務局のアプリを作った方。名誉毀損で訴えてくれて構いません。法廷で徹底的にやり合いましょう。
To the person who made the Legal Affairs Bureau’s application: feel free to sue me for defamation. Let’s fight it out thoroughly in court.

あなた方のアプリが、管理者権限でOSやネットワーク設定に手を入れ、PCのリソースを消費し尽くし、結果として利用者の作業環境を破壊したことについて、私は、うんざりするほどの証拠を揃えて白日の下に晒す覚悟があります(本気です)。
I am fully prepared—seriously—to present overwhelming evidence in public showing that your application, by modifying OS and network settings with administrative privileges and consuming PC resources, ultimately destroyed users’ work environments.

正確に言い直すなら、これっきりの話ではありません。
To be precise, this is not a one-time incident.

■Windowsの自動バージョンアップで壊され、
■ドライバの自動更新で壊され、
■Pythonの更新で環境を壊され、
■Docker Desktopの仕様変更で壊され、
そして今度は、
■自国の行政機関のアプリによって壊されました。

- Broken by Windows automatic updates,
- broken by automatic driver updates,
- broken by Python updates that destroyed the environment,
- broken by specification changes in Docker Desktop,
and now,
- broken by an application from my own country’s government agency.

私は一体、どれだけの時間を「PCを使うため」に費やしてきたのでしょうか。
How much time have I spent just trying to be able to “use a PC”?

壊されて、直して、また壊されて、また直す。
Broken, fixed, broken again, fixed again.

この繰り返しに、一体どれほどの生産的価値があったのか、今となっては疑問しか残りません。
At this point, I can only question how much productive value this endless cycle has actually had.

ITエンジニアでなければ、「パソコンが壊れました。ですから今日は何もできません」と言うことが許されるのでしょうか。
If you are not an IT engineer, are you allowed to say, “My computer is broken, so I can’t do anything today”?

ITエンジニアではない人々は、このPCという道具による破壊行為と、どのように折り合いをつけて生きてきたのか。正直、一度聞いてみたいものです。
I want to ask how people who are not IT engineers have come to terms with the destruction caused by the tool known as the PC.

今朝も、私の許可を得ることなく、iPhoneは勝手にバージョンアップしていました。
This morning, my iPhone updated itself without my permission.

そして、iPhoneのバージョンアップもまた、一定の確率で不具合や作業妨害を引き起こしています。
iPhone updates also cause malfunctions and work disruptions with a certain probability.

私たちには、「望んでいないバージョンアップを拒否する権利」すら与えられていないのでしょうか。
Do we not even have the right to refuse updates we do not want?

なぜ、このような技術的暴力が、当然のものとして社会に受け入れられているのか、私には理解できません。
I cannot understand why this kind of technological violence is accepted as something normal in society.

----

どの政党も、消費税、物価高、所得倍増、企業の内部留保、富裕層への重課税 ーー 同じ言葉を繰り返すばかりです。
Every political party merely repeats the exact phrases: consumption tax, rising prices, income doubling, corporate retained earnings, and heavier taxation of the wealthy.

どの政党も同じことを言うのであれば、どこに投票しても同じだ、という結論にしかなりません。
If all parties say the same things, the only conclusion is that it makes no difference where you cast your vote.

■ 所得倍増を言うなら、数値目標を示せ。
- If you talk about doubling income, show numerical targets.

■企業の内部留保を問題にするなら、その企業を名指ししろ。
- If you claim corporate retained earnings are a problem, name the companies.

■富裕層への重課税を言うなら、その「富裕層」が誰を指すのかを定義しろ。
- If you argue for heavier taxation of the wealthy, define exactly who you mean by “the wealthy.”

そして、
And then,

■我が国の移民政策とは、一体何なのかを、いい加減はっきりさせろ。
- Make it clear, once and for all, what our country’s immigration policy actually is.

私は以前、外国人労働者の実態を調べたことがありますが、当時見えてきたのは、移民政策などという立派なものではなく、外国人労働力の使い捨てと、役目が終わった後の帰国を前提とした制度設計でした。
I once investigated the realities faced by foreign workers, and what I saw was not anything as grand as an immigration policy. Still, it is a system designed around the use of disposable foreign labor and repatriation once their role is complete.

その後、理念としての移民政策が明確に示されたとは、少なくとも私は聞いていません。
At least as far as I know, no clear immigration policy based on a coherent理念 has been presented since then.

(↑クリックすると、コラム「外国人就労拡大で際立つ日本の「ブラック国家ぶり」」に飛びます)
(↑ Click on the column)

抽象論の演説には、もう聞き飽きました。
I am already tired of abstract speeches.

正直に言えば、不快です。
To be honest, they are unpleasant.

具体的かつ定量的に語れないのであれば『黙っていろ』。
If you cannot speak concretely and quantitatively, then shut up.

---

ともあれ ――

Anyway,

「望んでいないバージョンアップを拒否する権利」の法制化を明確に掲げる政党があれば、私は、迷わず票を投じることは約束します。
If there is a political party that clearly advocates the legal right to refuse unwanted updates, I will vote for it without hesitation.

『行政府が提供するアプリを使うと、下手なウィルスより、酷い結果が待っている』 『メインのPCには絶対にインストールしないこと』

2026,江端さんの忘備録

今回は私の自作MAS(マルチエージェントシミュレーション)、「EBASim(Embedded Behavioral Agent Simulation:心理モデル組込型エージェント・シミュレーション)」について説明します。EBASimを開発したのはいいものの、その後、ある絶望的な課題が浮かび上がってきます。

3年間の休載を経て戻ってきました。休載していた理由は、私はリタイア(定年退職)間際だったにもかかわらず、「MAS(マルチエージェントシミュレーション)」を研究すべく、社会人のまま大学院博士課程に突っ込んでいったからです。なぜ“そんなこと”になったのか――。そして私をそこまでさせた「MAS」とは何なのか。社会人大学院生の実態を赤裸々に語りつつ、MASを技術的に深掘りしていきます。
⇒連載バックナンバーはこちらから

前編「定年間際のエンジニアが博士課程進学を選んだ「本当の理由」」

2026,江端さんの忘備録

今回は、リタイア目前だった私が、博士課程進学を選んだ理由についてお話します。いろいろと条件が重なったというのもあるのですが、最後の最後に、私を進学へと駆り立てたのは、随分前から抱いていた、ある「疑問」でした。

2026年02月04日 15時30分 公開
[江端智一,EE Times Japan]

3年間の休載を経て戻ってきました。休載していた理由は、私はリタイア(定年退職)間際だったにもかかわらず、「MAS(マルチエージェントシミュレーション)」を研究すべく、社会人のまま大学院博士課程に突っ込んでいったからです。なぜ“そんなこと”になったのか――。そして私をそこまでさせた「MAS」とは何なのか。社会人大学院生の実態を赤裸々に語りつつ、MASを技術的に深掘りしていきます。

2026,江端さんの忘備録

東京(関東エリア)は、昨年、大きな台風の被害もなく、洪水なども発生せず、そして、自衛隊が出動するという「住民の生存を左右しかねない」豪雪もありませんでした。
Last year, Tokyo (the Kanto region) experienced neither significant typhoon damage nor flooding, nor did it suffer heavy snowfall severe enough to require the deployment of the Self-Defense Forces, which could potentially determine residents' survival.

(まあ、酷暑災害はありましたが、これは日本人全員が被害者でしたから)
(There was, of course, extreme heat, but in that case, all Japanese were victims.)

―― 絶対、どこかで、この負債を支払わなければならない
と、私は怯えています。
And yet, I fear this debt will inevitably have to be paid somewhere, someday.

とはいえ、統計を取り扱うエンジニアとしては、これはおよそ合理的とは思えない感情でもあります(「ギャンブラーの誤謬」という用語で検索してみて下さい)。
That said, as an engineer who works with statistics, I recognize that this feeling is hardly rational (see the term "gambler's fallacy").

その不安のトップにあるのが「大地震」で、その次には「富士山の噴火」です。もちろん、洪水などの水害はデフォルトです。以前もお話ししましたが、東京の河川付近一帯は、例外なくハザードマップ上で"真っ赤"です。
At the top of my list of anxieties is a significant earthquake, followed by a possible eruption of Mount Fuji. Flood-related disasters are, of course, a given. As I have mentioned before, areas along Tokyo's rivers are, without exception, marked in deep red on hazard maps.

天災に弱すぎる――具体的には、たった1cmの積雪で、当日はもちろん、その後数日間は交通混乱が避けられないほど、この街は懦弱です。
This city is far too vulnerable to natural disasters, so much so that even a mere one centimeter of snowfall can cause traffic chaos not only on that day, but for several days afterward.

---

何かのコラムで読みましたが――
I once read in a column

最近の豪雪災害のニュースを見ていると、「東北の人々は、この被害だけで、その土地を捨てて逃げようとは思わないのか?」と、つい考えてしまいます。しかし一方で、東北の人々は、「東京に住んでいる人は、あんな災害に弱い街に住んでいるのか?」と思っているようです。
When watching recent news about heavy snowfall disasters, I find myself wondering, "Don't people in Tohoku ever consider abandoning their land and fleeing after experiencing such damage?" Yet at the same time, it seems that people in Tohoku think, "People in Tokyo live in a city that is that vulnerable to disasters?"

一回の大地震で、数万人から十数万人の死者が想定されている街――それにもかかわらず、なぜこんな街の地価が上昇するのか、不思議に感じることがあります。
This is a city where a single major earthquake is expected to result in tens or even hundreds of thousands of deaths, and yet, I cannot help but find it puzzling that land prices continue to rise.

加えて言えば、東京は間違いなく外国からミサイルロックオンされている街です(多分、同盟国でさえロックしていると思います)。軍事力の意思決定拠点(行政、国会、自衛隊の司令部)が集約している街でもあります。我が国(の軍事力……もとい、防衛力)を無力化するなら、ここを一撃するのが最も手っ取り早いことは、私にでも分かります。
In addition, Tokyo is undoubtedly a city targeted by foreign missile locks (probably even by allied nations). It is a city where centers of military decision-making, administrative bodies, the National Diet, and the headquarters of the Self-Defense Forces are concentrated. If one wanted to neutralize our country's military power, pardon me, defense capability, it is obvious even to me that striking here would be the quickest way.

---

この矛盾を「経済合理性」で説明しようとすると、たいてい話は破綻します。
When one tries to explain this contradiction in terms of economic rationality, the argument usually falls apart.

期待値で見れば、明らかに割に合いません。被害確率は低いものの、発生時の損失が巨大すぎるからです。
From an expected-value perspective, it clearly does not pay off. Although the probability of damage is low, the losses incurred if it occurs are too significant.

それでも人は集まり、地価は上がり、インフラはさらに集約されています。
Yet people continue to gather, land prices rise, and infrastructure becomes even more concentrated.

渋谷駅の鉄道インフラ大改造(キャッチコピーは「100年に1度の大改修」)を扱ったNHK特集は大変面白かったのですが、私は――「渋谷の街が、大地震と大火災で灰燼に帰した後で、やればいいじゃないか」と思ってしまいました。
An NHK special on the massive redevelopment of Shibuya Station's rail infrastructure (branded as "the once-in-a-century renovation") was fascinating. Still, I found myself thinking, "Why not just do it after Shibuya has been reduced to ashes by a major earthquake and fire?"

おそらく、私と同じように考える人(特に幹部クラスの年配者たち)は、そこそこ多かったのではないかと思います。それでもこの大改造を敢行した中堅管理職(?)の政治力と、それを実行した技術者たちの実行力の方に、私はむしろ感心してしまったのです。
I suspect many people shared my view, especially older executives. Even so, I found myself more impressed by the political clout of the mid-level managers who pushed this project through, and by the execution capability of the engineers who carried it out.

閑話休題。
Now, to return to the main topic.

---

通勤が楽であること、仕事があること、病院が近いこと、文化が集中していること。これらは毎日効いてくる効用です。一方で、地震や噴火は「まだ起きていない」未来の話です。
Ease of commuting, job availability, proximity to hospitals, and cultural concentration are benefits that affect every day. Earthquakes and eruptions, on the other hand, are future events that "have not yet happened."

こうして、「日常の利便性」が「非日常の破局」を塗り潰していきます。
In this way, the convenience of everyday life paints over the prospect of extraordinary catastrophe.

人間は、確率よりも体感を重視する生き物です。毎日感じる快適さは、年に一度も感じない不安より、はるかに強く作用します。
Human beings prioritize lived experience over probability. Comfort felt every day exerts a far stronger influence than anxieties felt less than once a year.

だからこそ、東京は「合理的に危険な都市」でありながら、「感情的に正解な都市」であり続けてしまいます。この二重構造が、都市の脆さを覆い隠しているのです。
That is why Tokyo remains a city that is rationally dangerous yet emotionally correct. This dual structure conceals the city's fragility.

さらに言えば、東京という街は「逃げにくい」構造を、自ら作り続けています。
Furthermore, Tokyo continues to develop a structure that impedes escape.

住宅価格の高騰は住民の可動性を奪い、職の集中は代替地を消し、インフラの巨大化は撤退コストを引き上げます。
Rising housing prices strip residents of mobility, job concentration eliminates alternatives, and massive infrastructure investments increase the cost of withdrawal.

その結果、「危ないと分かっていても離れられない」という、静かなロックインが進行します。
As a result, a quiet lock-in ensues, in which people understand the danger yet cannot leave.

災害に強い街とは、単に堤防が高い街ではありません。住民が「動ける」街です。一時的にでも離脱でき、別の場所で生活を継続できる余地がある街です。
A disaster-resilient city is not simply one with high levees. Is it a city where residents can move to a town that allows temporary evacuation and the possibility of continuing life elsewhere?

以前、私は自分の町内の地図を俯瞰してみたことがありますが、そのとき正直、青冷めました。町内からの脱出ルートが4本しかなく、そのうち2本は地震で寸断される可能性が高いと感じたからです。
Once, when I looked down at a map of my neighborhood from above, I honestly turned pale. There were only four evacuation routes out of the area, and I felt that two of them were highly likely to be cut off in an earthquake.

---

ともあれ、「絶対、どこかで、この負債を支払わなければならない」とは思っていますが――
In any case, I do believe that this debt will inevitably have to be paid somewhere, someday.

その支払いは、「私がいなくなった後がいいな」とも思っています。
But I also hope the payment will come after I am gone.

逃げきれるか、どうか。「自然災害 vs 私の寿命」を、ChatGPTに計算してもらいました。
I asked ChatGPT to calculate whether I can escape "natural disasters versus my remaining lifespan."

まあ、その計算結果を本気にしているわけではありません。ただの、ちょっとした気休めです。
I am not taking the result seriously, of course. It is merely a small source of comfort.

====== ChatGPTによるフェルミ推定結果 ======

自身が"致命的または生活継続不能級"の直撃を受ける(死亡、または長期避難・資産喪失・就労不能などで生活が崩壊)と定義します。「あなたが先に勝つ」は、**それが起きる前に寿命が先に尽きる(あるいは直撃を受けずに過ごせる)**です。

1) 残り寿命(ざっくり)

60歳からの残り寿命は、フェルミでは 25年(85歳) を基準に置きます。(20年-30年の幅でも後で感度を出します。)

2) 年あたりの「直撃(生活崩壊級)」確率 p を置く

ここが肝です。

「首都圏で大きい地震が起きる確率」ではなく、あなたの生活が"壊れるレベル"で当たる確率なので、年あたり 0.5%-2% くらいのレンジを置くのがフェルミとして妥当だと思います。

0.5%/年:大災害は起きても「自分は致命傷を外す」寄り(耐震・立地・運)

1%/年:そこそこ現実的な中庸

2%/年:地震・水害・猛暑・広域ライフライン断などを広めに取り、「生活崩壊」判定も厳しめ

3) 生涯(残り25年)で直撃する確率

独立近似で、累積確率は

P(直撃)=1 (p)^N(N=25年)です。

p=0.5% → 0.995^25 ≒ 0.882 ≒ 11.8%

p=1% → 0.99^25 ≒ 0.778 ≒ 22.2%

p=2% → 0.98^25 ≒ 0.603 ≒ 39.7%

よって「あなたが勝つ(直撃を食らわずに寿命が先に来る)」確率は P(直撃) なので、

楽観(p=0.5%):約88%

中庸(p=1%):約78%

厳しめ(p=2%):約60%

4) 感度(残り寿命が20年/30年なら)

p=1%で見ると、

N=20年:0.99^20 ≒ 18.2% → 勝率 約82%

N=30年:0.99^30 ≒ 26.0% → 勝率 約74%

つまり、このゲームは寿命よりも p(年あたり直撃率)をどう置くかで結果が大きく動きます。

結論(フェルミ)

あなたが60歳で東京(関東)に住み続ける前提なら、自然災害 vs あなたの寿命 の勝率(あなたが勝つ)は、ざっくり 60-90%、中庸で約75-80% という見積もりになります。

この勝率を上げる"現実的なレバー"は、地震そのものの確率を議論するより、「直撃(生活崩壊級)」の p を下げる方向です。耐震等級、ハザード(浸水・土砂)からの距離、高層エレベータ依存の低減、備蓄、家族の集合手順、職住の冗長化、このあたりが全部 p に効きます。

====== ChatGPTによるフェルミ推定結果 ここまで ======

2026,未分類

昨日の日曜日、嫁さんと二人で、2km先にある市民センターまで「期日前投票」をしに、歩いて行ってきました。
Yesterday, my wife and I walked together to the civic center, 2 kilometers away, to cast an early vote.

以前にも、同じように歩いて行って「今日はやっていません」と言われたことがあり、正直、嫌な予感はしていました。
I had once walked there in the same way before, only to be told, "It’s not being held today," so to be honest, I had a bad feeling this time as well.

それでも今回は、
Even so, this time,

(1) 最高裁判官国民審査が2月1日から可能になる
(1) The Supreme Court justice review would be possible starting February 1,

(2) 投票日まで1週間もない状況で、期日前投票をやっていないわけがない
(2) and with less than a week remaining before election day, there was no way early voting wouldn’t be available,

と考え、「さすがに今回は大丈夫だろう」と判断しました。
So I thought, "Surely this time it will be fine," and made my decision.

---

結果、市民センターの入口には、
As a result, at the entrance of the civic center,

「期日前投票は2月3日(火)からです」
"Early voting starts on Tuesday, February 3."

という紙が、これ以上ないほど静かに貼ってありました。
was written on a piece of paper and posted with an almost unsettling calm.

もちろん、事前に確認もしなかった私が悪いです。そこは否定しません。全面的に私のミスです。
Of course, it was my fault for not checking in advance. I don’t deny that at all. It was entirely my mistake.

しかし、それを差し引いても、どうしても納得できない。
But even after accounting for that, there is something I cannot accept.

―― 期日前投票が、投票直前の休日にできないって、何なんでしょうか。
"What does it mean that early voting isn’t available on the weekend just before election day?"

平日は仕事で動けない。
On weekdays, I can’t move because of work.

投票日はすでに予定が入っている。
On election day, I already have plans.

だからこそ「期日前投票」という制度があるはずです。
That is precisely why an "early voting" system exists.

にもかかわらず、その期日前投票が、休日に使えない。
And yet, early voting cannot be used on a weekend.

これは単なる「不便」ではありません。
This is not a mere inconvenience.

『制度として、結果的に投票を妨げている』としか思えません。
I can only see it as a system that, in effect, obstructs voting.

さらに、今回は最高裁判官国民審査があります。
Moreover, this election includes a review of the Supreme Court justices.

これは2月1日以降でなければ行使できません。
This cannot be exercised until February 1.

結果として私は、
As a result, I was pushed into the following situation:

- 休日(先週の週末)は使えなかった
- I couldn’t use the weekend (last weekend),

- 平日には行けない(定時後も仕事がある)
- I can’t go on weekdays (my work schedule is packed),

- 投票日当日には予定がある
- and I have plans on election day itself.

という状況に追い込まれました。
That is the situation I was forced into.

―― 投票したくても、投票ができない。
"Even though I want to vote, I cannot vote."

これは、どう言い繕っても、『事実上の選挙(投票)妨害』です。
No matter how you dress it up, this is effectively an inability to exercise my right to vote.

---

念のために言っておきますが、今回の選挙日程が「違法」だとは言いません。
To be clear, I am not saying that this election schedule is illegal.

法律上は、問題ありません。
Legally, there is no problem.

衆議院解散の根拠は、日本国憲法第7条にあります。
The basis for dissolving the House of Representatives is Article 7 of Japan's Constitution.

「天皇は、内閣の助言と承認により、国事行為として衆議院を解散する」
"The Emperor, with the advice and approval of the Cabinet, shall dissolve the House of Representatives as an act of state."

実務上は、内閣(=首相)が事実上の裁量で解散時期を決められる、という運用が確立しています。
In practice, an established convention allows the Cabinet (that is, the Prime Minister) to decide the timing of dissolution at its own discretion.

ここには、「○日前に予告せよ」や「国民生活への配慮義務」といった条文上の制約はありません。
There are no statutory constraints such as "advance notice X days beforehand" or "an obligation to consider citizens’ daily lives."

だから、この選挙そのものに違法性はないのです。
That is why there is no illegality in this election itself.

では、やろうと思えば「解散の次の日に選挙」ができるのかというと、これもできません。
Then, if one really wanted to, could an election be held the day after dissolution? The answer is no.

公職選挙法によれば、最低でも12日は必要とされているからです。
According to the Public Offices Election Act, a minimum of 12 days is required.

つまり、
In other words,

『法律上は、解散の翌日に選挙はできないが、生活者が対応できないほど短い日程は、合法的に設定できる』
"Legally, an election cannot be held the day after dissolution, but a schedule so short that ordinary people cannot cope with it can still be set lawfully."

ということになります。
That is what this means.

[データ]
[Data]

- 今回の選挙戦期間(公示→投票)は、過去の例と比べてかなり短く、制度上の最短限界です。
- The campaign period in this election (from official announcement to voting day) is significantly shorter than in past cases and is set at the minimum limit allowed by the system.

- 従来の平均値は約18~20日間程度で、今回の12日間はそれより6~8日(約1週間)短いです。
- The conventional average is approximately 18 to 20 days, meaning that the current 12-day period is 6 to 8 days (about one week) shorter than usual.

---

しかし、私は声を大にして言いたい。
However, I want to say this loudly and clearly.

―― 合法であれば、何をやってもいいのか
"If it is legal, does that mean anything goes?"

この日程設定は、首相の解散権という、極めて強力な権限を使って、「投票できない人が出ることを、結果として許容する形で」行われたものです。
This scheduling was carried out by exercising the Prime Minister’s compelling authority to dissolve the Diet, in a way that ultimately tolerates the emergence of people who cannot vote.

それを私は、『解散権の濫用』と呼ばずに、何と呼べばいいのか分かりません。
Can I not see this as anything other than an abuse of the power of dissolution? I don’t know what else to call it.

行政の現場を責める気はありません。彼らは、決められた日程に従って業務をしているだけです。
I have no intention of blaming those working on the administrative front lines. They are simply carrying out their duties calmly according to the set schedule.

問題は、この日程を選び、その結果として国民の一部が投票からこぼれ落ちることを、『解散権の行使者が"無視"したことそのもの』です。
The problem lies with those who chose this schedule and who do not consider it a problem that, as a result, a portion of the electorate is excluded from voting.

私は今回、棄権します。というより、『棄権せざるを得ません』。
This time, I will abstain from voting. Or rather, "I am forced to abstain.2

投票したくないからではありません。政治に興味がないからでもありません。『投票できないようにされた』からです。
It is not because I do not want to vote. Nor is it because I am uninterested in politics. It is because I was made unable to vote.

---

それにしても ――
Even so,

『このことに、心底腹を立てているのは、私だけ』なのでしょうか。
Am I really the only one who is angry?

『今回の選挙戦期間(公示→投票)が短いことは与党にとってメリットに働くものですか?』とChatGPTに聞いてみた件

2026,江端さんの忘備録

昨日、データベースにアクセスして情報を入手する必要があったのですが、アクセスポイントが分からず、スキーマも不明のままで対応に困っていたところ、ChatGPTが一般的な設計慣習から「可能性の高いパラメータ」を推定し、そのアクセスポイントを言い当て、想定されるスキーマ構造まで構築して見せました ―― 正直、ゾッとしました。
Yesterday, when I needed to retrieve information from a database but lacked the access point or schema, ChatGPT inferred likely parameters based on standard design conventions, correctly identified the access point, and even constructed a plausible schema. Honestly, it sent a chill down my spine.

以前、高校生が生成AIを用いてクレジットカード情報の不正取得を補助し、結果として不正行為に成功したというニュースを聞きました。私は今日、そのニュースを「遠い世界の話」だとは思えなくなりました。
I once heard a news story about a high school student who used generative AI to help commit the illegal acquisition of credit card information, ultimately succeeding in the fraud. Today, that story no longer feels like something from a distant world.

その高校生が「間抜け」だった点は、それを他人に自慢していた、という一点に尽きます。正直『ガキだな』と思いました。
The one truly foolish thing the student did was to boast about it to others. Frankly, I thought, "What a kid."

---

私がシステムをクラックする側になるなら「同じ対象に二度とアクセスしない」という原則だけは守るでしょう。
If I were on the malicious side, the one rule I would strictly follow is never approaching the same target twice.

生成AIによって侵入のしきい値は格段に低くなっています。「一撃離脱」を徹底すれば、追跡は相対的に困難になります。これから、システム侵入を試みる人間が増えるのは、むしろ自然です。
With generative AI, attempts at intrusion have become dramatically easier. If "hit-and-run" tactics are thoroughly applied, tracking becomes relatively complex. It is only natural that more people would come to think this way.

私が言いたいのは、『攻撃が、驚くほど安く、簡単に、再現性のある行為になりつつある』という現実です。そして、その知識を持つ人間が、もはや一部の専門家ではなくなってきている、という点です。
What I am saying is not that the number of attackers has increased. It is the reality that attacks are becoming astonishingly cheap, clever, and reproducible, and that such knowledge is no longer confined to a small group of specialists.

犯罪者の無知に期待する時代は、終わりつつあります。まだそれに望みを託している人がいるとすれば、それは楽観ではなく、思考停止です。
The era of relying on criminals’ ignorance is over. If anyone is still betting on that, it is not optimism but a failure to think.

では、どうするのか
So, what should we do?

私がたどりついた解は、「IT化・DX化からの撤退」です。
The conclusion I arrived at is "withdrawal from ITization and DX."

---

「いよいよ江端が狂ったか?」と思われるかもしれません。しかし、私の知る限り、この選択肢を真面目に検討した人を、私は知りません。
Some may think, "Has Ebata finally lost his mind?" However, to my knowledge, no one has seriously examined this option.

だからこそ、一度くらい、真顔で考えてみてもいいと思いました。
That is precisely why I believe it is worth considering at least once, seriously.

ここで言う「完全撤退」とは、ITを使わない、という話ではありません。
By "withdrawal," I do not mean abandoning IT altogether.

DXという、「長期間」「きちんと」「多人数で」「統一的に」使えるシステムを作ろうとする発想から撤退する、という意味です。
I mean, withdrawing from the mindset of DX that seeks to build systems that are "for the long term," "properly," "by many people," and "in a unified manner."

現場の人間がPCを使うのは構いません。Excelで計算してもいいし、スクリプトを書いてもいい。ただし、それを組織の"公式システム"にしない。情報共有も、統一基盤など作らず、メールやチャットで場当たり的にやる。
It is fine for people on the ground to use PCs. They can calculate with Excel or write scripts. However, those should not become the organization’s "official systems." Information sharing should also be ad hoc, via email or chat, rather than by building a unified platform.

現場が勝手に小さな仕組みを作り、飽きたら捨てる。一定期間使われなければ、自動的に壊れて消えるようにしておく。そういう、『雑で、局所的で、無責任に見えるIT運用』です。
The field creates small mechanisms at will and discards them when they are no longer helpful. If something is not used for a specific period, it degrades and disappears. This is a form of IT operation that looks messy, local, and irresponsible.

---

これは何も新しい話ではありません。
There is nothing new about this.

現実世界の業務は、もともとこうです。ホワイトボードは消され、メモは捨てられ、やり方は人が変われば変わる。それを、ITの世界だけ「10年使える統合システム」にしようとするから、悲劇が始まるのです。
This is how work in the real world has always been. Whiteboards are erased, notes are discarded, and methods change as people change. Tragedy begins when only the IT world tries to make "integrated systems that last ten years."

IT技術は毎年変わり続けます。OSも言語もフレームワークも、セキュリティの前提も変わり続けています。そんな世界で「10年間連続で使えるシステム」を作ろうとするのは、はっきり言って「思い違い」をしています。
IT keeps changing every year. Operating systems, languages, frameworks, and security assumptions all continue to evolve. Trying to build a system that lasts ten years in such a world is, quite frankly, a conceptual mistake.

そもそも、10年以上、全く運用が変わらなかったシステムなんて、あるのでしょうか(メールシステムくらいかな)。
Is there a system that has operated for more than 10 years without any change? (Perhaps only email systems.)

結果として、誰も好んで使わない巨大な負債が生まれ、しかも攻撃者にとっては、実に親切な金庫になります。
As a result, substantial liabilities that no one wants to assume are created. and they become extremely considerate vaults for attackers.

比べて、現場で小さく作られた仕組みは、攻撃対象として魅力がありません。
By contrast, small mechanisms created locally on the ground are not attractive targets.

集約されていない。寿命が短い。壊れても影響が限定的。守る価値がないものは、狙われません。これは高度なセキュリティ対策ではなく、『単なる経済原理』です。
They are not centralized. Their lifespans are short. Even if they break, the impact is limited. Things not worth protecting are not targeted. This is not an advanced security measure but simply an economic principle.

---

DXとは、業務をデジタルにすることではありません。業務を「長期間・統一的に固定する」という思想です。
DX is not about digitizing work. It is a philosophy of fixing work in a unified form over the long term.

そして私は、その思想こそが、いま一番危険だと思っています。
And I believe that this very philosophy is the most dangerous thing right now.

こちらが「ちゃんとしたDXシステム」を作るたびに、「ここに価値があります」「ここを狙ってください」という案内板を、律儀に立てていることに、気づいてしまったからです。
Because I have finally realized that every time we build a "proper DX system," we are dutifully putting up signposts saying, "Value is here" and "Please target this."

AIはそういうものを見つけるのが、とても得意です。ちゃんとしたDXシステムになればなるほど、AIにネタを提供しているようなものです。
AI is extremely good at finding such things. The more "proper" a DX system becomes, the more it feels like we are handing AI material to work with.

比して、集約されていない。寿命が短い。壊れても影響が限定的なシステムは、小さく、汚く、バラバラで、すぐ消える。誰も全体を把握できない ―― それは、攻撃者から見れば「金庫」ではなく、「触る気もしないゴミの山」です。
By contrast, systems that are not centralized, have short lifespans, and cause limited damage when they fail are small, messy, fragmented, and quickly disappear. Can no one grasp the whole? From an attacker’s perspective, they are not vaults but piles of garbage, not even worth touching.

これからの時代、『一番セキュリティが高いITシステムとは、誰も「システム」だと思っていないもの』なのかもしれません。
In the coming era, the most secure IT systems may be those no one even considers "systems."

---

もっとも、こんな話を真面目に聞いてもらえるとは、私自身、期待していません。
That said, I myself do not really expect anyone to take this talk seriously.

それに、私の頭の中には、こんな反論も聞こえてくるんですよ。
And in my head, I can already hear a counterargument like this.

「『医療』『金融』『社会インフラ(水、電気、ガス、情報)に通用する話になっているのか」と ―― 特に「マイナンバーカードのシステム」は、その代表格です。
"Does this argument really apply to healthcare, finance, or social infrastructure such as water, electricity, gas, and information?" The My Number card system is a prime example.

私のしょぼいWebシステムですら、毎日数千以上の攻撃を受けています(いや、本当です。ログを見てうんざりしています)。ましてや、「マイナンバーカードのシステム」という日本システムへの本土攻撃は、シャレにならないレベルになっているはずです。
Even my modest web system is subjected to several thousand attacks every day (no exaggeration—I’m honestly fed up after looking at the logs). When it comes to a national system for all Japanese citizens, such as the “My Number Card,” the level of direct cyberattacks must be on an entirely different, far more serious scale.

これも、システムの分散化によって、ある程度の対応が可能になるとは思います ―― 残っている課題は、そのようなシステムを攻撃された時のリスク計算だけです。
Even here, I believe a certain level of ?? is possible through system decentralization. The remaining question is whether the risks associated with such systems when attacked are being properly weighed.

---

なぜシステムを攻撃するのか? そこにシステムがあるから ――
Why attack a system? Because there is a system there.

別段、登山者でなくても、そう考えてしまう人間が一定数いる、という前提でITシステムは設計されているはずです。
This should be designed assuming that a certain number of people will hold this view, even if they are not mountaineers.

なにしろ、ITシステムは自宅のPCから、誰でも辿りつけます。
After all, IT systems can be accessed by anyone from a home PC.

なにしろ、年齢制限も、免許も、覚悟も要らない。
No age restriction, no license, and no resolution are required.

『サイバー攻撃の真の恐しさを理解していない人が、まだこんなにもいる』ということに、震撼しました。

2026,江端さんの忘備録

博士号取得と、父と母の法要を兼ねた食事会の場で、姉からお祝いを貰いました。
At a dinner gathering to mark both the completion of my doctoral degree and the memorial service for my father and mother, my older sister gave me a celebratory gift.

現金10万円 ―― その気持ちが、とても嬉しかったです。
Cash: 100,000 yen—the sentiment behind it made me genuinely happy.

問題は、「私が、まだ、その現金10万円の使い道で困っている」ということです。
The problem is that I am still at a loss about how to use that 100,000 yen.

---

以前、私は、難しい資格試験に合格した親戚に、同程度のお金をお祝いとして渡したことがあります。
Some time ago, I gave a similar amount of money as a gift to a relative who had passed a difficult qualification exam.

その際、
At that time,

―― 新車の購入の金額に充てる
"It would be put toward the purchase of a new car."

と聞いて、お祝いの気持ちが、いっきに萎えてしまったのを覚えています。
And I remember my sense of celebration deflating all at once when I heard that.

もちろん、お祝いのお金ですので、それを何に使うのかは、その人の完全な自由です。
Of course, since it was a celebratory gift, how the money was used was entirely up to that person.

しかし私は車に興味がないため、正直なところ、がっかりしてしまったのです。
However, because I have no interest in cars, I was honestly disappointed.

分かっています。これは、私の酷く勝手な言い分です。
I know this is an extremely selfish way of thinking on my part.

つまり私は、
In other words, I wanted either

(1)「私の望む形のお金の使い方」を表明してくれるか、
(1) that they would state a use of the money that aligned with what I hoped for, or

(2)『まだ決めていない』と、使い道を"陽"にしないで欲しかったのです。
(2) that they would say, "I haven't decided yet," and keep the use of the money from being explicitly revealed.

繰り返しますが、上記の(1)であれ(2)であれ、そんなことを思ってしまう「私が悪い」
I repeat: whether it was (1) or (2), the fact that I thought such things means that I am the one at fault.

というか、「私の度量が狭い」のです。
Or rather, it shows how narrow-minded I am.

---

まあ、そんなこともあって、姉には「お祝いのお金を◯◯に使わせてもらったよー」と、私の(×姉の)望む形で報告したいのです。
Because of all this, I want to report to my sister, "I used the celebratory money for ◯◯," in a way that satisfies *my* wishes (not necessarily hers).

この件について、またもやChatGPTに相談してみました。以下が、その回答です。
Regarding this matter, I once again consulted ChatGPT. The following is its response.

===== ChatGPT回答ここから ======
===== ChatGPT response begins here ======

要点は単純で、「何に使うか」そのものよりも、「その使い道が、祝ってくれた人の気持ちをどう完結させるか」と『あなた(江端さん)がどのように考えるか』が重要なのだ、ということでしょう。
The point is simple: what matters is not so much what the money is used for, but how that use brings closure to the feelings of the person who offered the congratulations, and how you (Ebata-san) think about it.

お祝い金を"消費"に変えてしまうと、祝意は日常に溶けて消える。
If celebratory money is turned into mere "consumption," the sentiment of celebration dissolves into everyday life and disappears.

一方で、時間や体験、あるいは日常の中で繰り返し思い出される形に変換すれば、その祝意は長く残る、というわけです。
On the other hand, if it is transformed into time, experiences, or something that can be remembered repeatedly in daily life, the celebratory sentiment can last much longer.

例えば、ご両親のことを考えるための静かな時間や、一度きりの小さな旅。
For example, quiet time spent reflecting on one's parents, or a small, one-time trip.

あるいは、博士号という到達点を自分の中に定着させるための書籍や環境づくり。
Or books and an environment that help internalize the milestone of earning a doctoral degree.

また、自分一人では決して選ばないが、使うたびに「祝ってもらった記憶」が立ち上がるような日用品も、悪くない選択だとされています。
Everyday items that one would never choose on one's own but that evoke the memory of being celebrated each time they are used are also considered a reasonable option.

しかしながら、今回のケースでは、「あえて、まだ使わない」という選択肢をお勧めしたいと思います。
However, in this case, I would recommend deliberately not using the money yet.

軽く扱うには重すぎるお祝いだからこそ、専用の形で保留し、「これは使うべきだ」と思える瞬間まで寝かせておく。
Precisely because this is a gift too significant to treat lightly, setting it aside in a special way and letting it rest until the moment comes when you feel, "Now is the time to use it,"

その態度自体が、祝意への応答になり得ます。
That very attitude itself can become a response to the celebratory sentiment.

結局のところ、「正しい使い道」など存在せず、あるのは、「あなたが、納得できる物語」です。
In the end, there is no such thing as a "correct" way to use it; there is only the story that you yourself can accept.

===== ChatGPT回答ここまで ======

===== ChatGPT response ends here ======

なるほど、「保留」というのは良い方針であり、それは、まさに今、私がやっていることでもあります。
I see. "Holding it in reserve" is indeed a good policy, and I am doing exactly that right now.

というわけで、姉には、
So, to my sister,

『頂いたお祝いのお金は、今は使わずに、じっくり考えます。
"I will not use the celebratory money right away, and I will take time to think carefully about it.

今は取っておいて、博士課程と同じ研究を続ける上で必要になった本や資料、作業環境に使わせてもらおうと思っています』
For now, I plan to set it aside and use it for books, materials, or a working environment that I will need as I continue my doctoral research."

と報告しようかと思っています。
That is what I am thinking of telling her.

世間に背を向けて捻くれた考えを持つ私のような人間にも、こうした“可視化される瞬間”が発動するという事実に――何に対してなのか自分でも定かではありませんが――言語化できない感謝の念が湧きました。