2025,江端さんの忘備録

『なぜトランプ関税交渉で赤沢大臣は合意文書を作成しなかったか』という批判があるようですが、「日本のサラリーマンの多くが『そりゃ、そうなるだろう』と思っている」と、私は思っています。
There has been criticism of “Why didn’t Minister Akasawa create a written agreement in the Trump tariff negotiations?”, but I believe that many Japanese office workers think, “Well, of course that’s how it turned out.”

というのは、『明文化しない』という戦略があるからです。
That’s because there is a strategy of “not putting things into writing.”

---

私がよく覚えているのは、1972年の日中国交回復のための「日中共同声明」の作成において、日中双方の官僚と政治家が、この声明文の作成にあたり、「双方の国民にとって都合よく解釈できる文章」に全力を注いだという事実です。
What I vividly remember is that, during the drafting of the 1972 Japan-China Joint Communiqué to normalize diplomatic relations, officials and politicians from both countries devoted themselves to creating a text that the citizens of both nations could conveniently interpret.

まず(1)「台湾表現」から始めます。
Let’s start with (1) “the Taiwan wording.”

共同声明では、中国の「台湾は中華人民共和国の不可分の一部」という立場を、日本は「理解・尊重」と記しつつ、「承認」という言葉は頑として使いませんでした。
In the communiqué, China’s position that “Taiwan is an inalienable part of the People’s Republic of China” was described by Japan as “understanding and respecting,” while steadfastly avoiding the word “recognize.”

この一語の差で、日本は法的拘束を逃れ、中国は国内向けに「日本も一つの中国原則に沿った」と胸を張ることができるようになりました。
This single-word difference allowed Japan to avoid a legal obligation while enabling China to proudly tell its domestic audience, “Japan also follows the One China principle.”

私からすれば、これは国際交渉というより、夫婦喧嘩後の「ごめんと言ったの?」「お互いの立場を尊重したんだよ」という、湿り気を帯びた和解宣言にも見えます。
To me, this looks less like an international negotiation and more like a dampened reconciliation after a marital quarrel: “Did you say sorry?” “I respected your position.”

双方が「勝った感」を持って帰国する、という演出ができるのだから、Win-Winと言えます。
Since both sides can walk away feeling victorious, it’s a Win-Win.

次に(2)「異常な状態の終結」と日付の書き方です。
Next, (2) “Ending the abnormal state” and the way the date was written.

同じ声明で「これまでの不正常な状態は、この共同声明が発出される日に終了する」と書き、戦争の終結時刻も手続きもあえて省いていました。
In the same communiqué, it stated, “The abnormal state between the two countries will end on the day this communiqué is issued,” deliberately omitting the specific time or procedures for ending the state of war.

代わりに1972年9月29日という政治的ケジメの日付だけを明示しています。
Instead, it only specified the politically significant date of September 29, 1972.

これは私から見ると、「とりあえず今日から仲直りってことで」と言って記念日を設定するカップルのノリですね。
To me, this is like a couple saying, “Let’s just reconcile from today,” and setting an anniversary date.

翌日から再びケンカする可能性を誰も否定していないのに、カレンダーだけは堂々と「仲直りの日」だけを赤丸でデカデカと書き込む ーー この楽観主義と割り切りは、ビジネス交渉でも通用しますし、(後述しますが)私も使ってきました。
No one denies the possibility of fighting again the next day. Yet, the calendar proudly marks only the “reconciliation day” with a big red circle — this optimism and pragmatism work in business negotiations as well, and (as I’ll explain later) I’ve used it myself.

最後に(3)「1978年の反覇権条項」です。
Lastly, (3) the “anti-hegemony clause” of 1978.

日中平和友好条約では、中国は「いかなる国による覇権にも反対」と明記し、当時のソ連を意識して“反ソ”を強調しています。
In the Japan-China Peace and Friendship Treaty, China explicitly stated that it “opposes hegemony by any country,” emphasizing an anti-Soviet stance with the Soviet Union in mind.

一方、日本は「第三国との関係に影響を及ぼさない」という但し書きを挿入し、対ソ関係への延焼を防いでいます(もちろん、今となっては、『お前が"それ"言う?』と中国(政府)に突っ込みたくなるような内容ですが、これは当時の声明です)。
Meanwhile, Japan inserted a proviso that it “would not affect relations with third countries,” preventing the spread of tension to its relations with the Soviet Union (of course, now one might want to retort to the Chinese government, “You’re the one saying that?” — but this was the statement at the time).

これは合同飲み会で片方が「アイツ嫌い」と叫び、もう片方が「まあまあ、あの人も良いところあるから」と必死でフォローする光景に似ています。
This is like at a joint drinking party, where one person shouts, “I hate that guy,” and the other desperately tries to smooth things over by saying, “Come on, he has some good points too.”

そして帰宅後(自国に戻った後)には、両者とも「俺の方が上手く立ち回った」と自画自賛することができる訳です。
And when they get home (back to their own countries), both can boast, “I handled that better.”

この“国内用ドヤ顔”を、両国政府が両立させることこそ、外交文書づくりの真骨頂と言えます。
Allowing both governments to maintain this “domestic smug face” is precisely the essence of diplomatic document drafting.

-----

実際、私の仕事にも似たようなケースがありあす。
There are similar cases in my work.

私は時々ソフトウェア(のプロトタイプ)を外注するのですが、発注仕様書には基本要件だけを書き、専門家でないと分からない細部や、私の頭の中でさえまだ霧の中にある要件はあえて書きません(というか、書けません)。
I sometimes outsource software prototypes, but in the request specifications, I write only the basic requirements, deliberately leaving out details that only specialists would understand, or requirements that are still vague even in my mind (or cannot be articulated).

というのも、外注側も私も、実際に作り始めてから「あ、これも必要だ」「あれが足りない」と気づくことが多いからです。
This is because both the contractor and I often realize after starting development, “Oh, we need this too,” or “That’s missing.”

そして、その“後出し仕様”が納期を吹き飛ばすことは、度々も発生します。
And these “after-the-fact specifications” often blow the delivery schedule to pieces.

こうなると、発注したソフトウェアのどの機能を制限または断念するかが現場(つまり私の)判断になります。
At that point, it’s my on-the-spot decision as the client whether to limit or abandon certain features of the software.

ここが発注者である私の正念場です。ここで適正な判断をしないと、全員が不幸になるからです。
This is a critical moment for me as the client — without proper judgment, everyone ends up unhappy.

そして、こういう場面ではソフトウェアの知見を持つか否かで発注者の格差がはっきり出ます。
In such situations, the gap between clients with software knowledge and those without becomes very clear.

その機能の実現困難さを頭に思い描けない発注者は、受注者から見れば、最低かつ最悪の「プロジェクト破壊者」になります。困難さとコストと時間を、直感で理解できないと、プロジェクトが止まるからです。
A client who cannot visualize the difficulty of implementing a feature becomes, from the contractor’s perspective, the worst possible “project destroyer.” If they cannot intuitively grasp the difficulty, cost, and time required, the project will grind to a halt.

そして私が今でもコーディングをバチバチにやっていることは、この「プロジェクト破壊者」を避けるために、確実に役立っていると信じています。
And I believe that my still actively coding today is helping me avoid becoming such a “project destroyer.”

まとめますと、表向きは「双方の合意の下で決まった仕様」ではあるのですが、実態は「まず動き出してから、互いの都合の良い解釈で肉付けする」という共同作業は、他の分野では知りませんが、ソフトウェア(のプロトタイプ)開発の発注では必須事項です。
In summary, while outwardly it is “a specification decided by mutual agreement,” in reality, “starting first and then fleshing out details through mutually favorable interpretations” is, as far as I know, essential in outsourcing software (prototype) development.

-----

外交交渉とソフトウェア外注 ―― 一見まったく異なる分野ですが、「明文化しすぎないことが成功の鍵」という構造は共通しています。
Diplomatic negotiations and software outsourcing — while seemingly unrelated fields — share the same structure: “Not over-specifying is the key to success.”

外交では、あえて余白を残すことで双方が国内向けに有利な説明を可能にし、プロジェクトでは、仕様を柔軟に動かせる余地を残すことで、変化に対応できる。
In diplomacy, leaving room for interpretation allows both sides to present a favorable explanation domestically; in projects, leaving flexibility in the specifications allows adaptation to change.

この視点に立てば、赤沢大臣がトランプ関税交渉で合意文書を作らなかったのは、むしろ最適戦略とも言えます。
From this perspective, Minister Akasawa’s decision not to create a written agreement in the Trump tariff negotiations could be considered an optimal strategy.

文書化すれば、どちらか一方の国内世論にとって“不都合な証拠”になる。曖昧なままなら、双方が「自分たちの有利」を主張できる。
If put in writing, it could become “inconvenient evidence” for one side’s domestic audience; left vague, both sides can claim “victory.”

これは単なる交渉テクニックではなく、外交も現場業務も貫く、社会に深く根付いた生存戦略なのです。
This is not just a negotiation technique, but a survival strategy deeply rooted in both diplomacy and field operations in the international community.

-----

…とはいえ、こうして「明文化しない戦略」の正当性を力説してきた私ですが、ここまで書いてふと我に返るのです。
…That said, after arguing so strongly for the validity of the “no-written-agreement” strategy, I suddenly find myself reflecting.

外交でもソフトウェア開発でも、「あえて書かない」ことには確かにメリットがある。けれど、その曖昧さが後で巨大な地雷になることも、これまた痛いほど経験してきました。
In both diplomacy and software development, there are indeed advantages to “deliberately not writing things down.” But I have also painfully experienced how that vagueness can later become a huge landmine.

赤沢大臣が合意文書を作らなかったのも、きっとその場では双方が「よし、これで丸く収まった」と思ったのでしょう。
When Minister Akasawa didn’t make a written agreement, I’m sure that at the time, both sides thought, “Alright, this wraps it up nicely.”

でも、時間が経つにつれ、「そんな約束してない」「いや、したはずだ」の応酬が始まり、結局は関係者全員が「あの時ちゃんと書いとけば…」と天を仰ぐ――そんな未来も、容易に想像できます。
But as time goes by, the back-and-forth of “We never agreed to that” and “Yes, we did” can begin, and I can easily imagine a future where everyone involved ends up looking to the heavens saying, “If only we had written it down back then…”

つまり、「書かない」は究極の保身策であると同時に、究極のブーメランでもあるわけです。
In other words, “not writing” is the ultimate self-protection measure, but also the ultimate boomerang.

外交でも現場でも、投げたブーメランが返ってくる速度と角度だけが違うだけで。
In both diplomacy and on-site work, the only difference is the speed and angle at which the thrown boomerang returns.

今回の交渉のケースが、後々“頭に直撃”にならないことを祈るばかりです。
I can only hope that Minister Akasawa’s case doesn’t later come back to hit him squarely on the head.

いや、正直、もう半分くらい当たってる気もしますが ーー 何しろ、交渉相手の性(たち)が悪すぎる。最悪です。
Honestly, I feel like it’s already halfway there — after all, the negotiating partner was far too formidable.

-----

今日は論じませんが、国際条約の勉強を(本当に必死で)やってきた人間の一人として、奴の「横紙破り」には心底頭にきているんですよ、私は。
I won’t be discussing it today, but as someone who has (truly desperately) studied international treaties, I am genuinely infuriated by that guy’s “high-handed disregard for the rules.”

「最恵国待遇の『撤回』」って、どの条文を適用するんだっけ?

2025,江端さんの忘備録

自称「特許明細書の製造装置」である私が、発明を考える方法は、「ノートを持ちあるいて、歩き回る」でした。
I, who call myself a "patent specification manufacturing machine," used to come up with inventions by “carrying a notebook and walking around.”

通勤でも散歩でもいいのですが、『目的地に到着する前に、かならず一つネタを出す』という決意で歩くことがキモでした。
Whether commuting or taking a walk, the key was my determination to “always produce at least one idea before reaching my destination.”

具体的には、基本的に頭の中に二人のペルソナを用意して、その二人を闘わせることを続けます ーー 一人が発明者としての私、そしてもう一人が特許庁審査官としての私です。
Specifically, I would prepare two personas in my head and make them fight—one as myself, the inventor, and the other as myself, the patent examiner.

私(発明者)の発明を、私(審査官)が潰し、それに対して、私(発明者)が反論をし、さらに私(審査官)が潰す、というバトルを頭の中に展開します。
The examiner-me would crush the inventor-me’s idea, to which the inventor-me would rebut, and then the examiner-me would crush it again—this battle would play out entirely in my head.

そして、最終的に、審査官の私を、発明者の私が論破できた時、発明が1つ完成する ーー そういうやり方でした。
And ultimately, when the inventor-me managed to refute the examiner-me, an invention would be considered complete—that was my method.

ところが、最近、この、「(歩き)ながら発明製造」という、私のメソッドを壊してくるものが登場してきました。
However, recently, something has emerged that disrupts my “invention manufacturing while walking” method.

ChatGPTです。
It is ChatGPT.

-----

ソフトバンクの孫社長が、『ChatGPTで多くの(数百?)の発明に辿りついた』という話を聞いた時、私は、意外とは思いませんでした。
When I heard that SoftBank’s CEO Masayoshi Son had “come up with many (over several thousant?) inventions using ChatGPT,” I was not surprised.

二人のペルソナのどちらかを、ChatGPTが担当してくれるからです。
ChatGPT can take on the role of one of my two personas.

正直に言って、ChatGPTからは、"イノベーティブ"な"モノ"は出てきません。
To be honest, ChatGPT does not produce anything truly “innovative.”

(ちなみに、私、"イノベーション"という言葉を濫用する近年の風潮が、あまり好きではありませんが、大学も会社も、その単語を含む部署に所属しています)
(By the way, I am not fond of the recent trend of overusing the word “innovation,” yet both my university and my company have departments with that word in their names.)

で、今度は、ChatGPTの出してきた"モノ"に対して、審査官としてケチをつけます ーー 『本当に、こんなネタで"進歩性"を回避できると思う?』と、嫌な聞き方をします。
Then, I nitpick what ChatGPT produces as the examiner—asking in an unpleasant tone, “Do you really think such an idea could avoid the ‘inventive step’ rejection?”

その上で、ChatGPTに対して、『自分で、このネタを潰すロジックを作ってみろ』と言います。
And then I tell ChatGPT, “Try coming up with the logic to destroy this idea yourself.”

うん、正直、こんなこと、ゼミ室や職場でやったら、間違いなくパワハラ案件です。
Yes, honestly, engaging in such behavior in a seminar room or workplace would be considered workplace harassment.

-----

ChatGPTと私の会話がスタックしてきたら、私が発明の想定環境を変える"状況"を提示します。
When my conversation with ChatGPT starts to get stuck, I present a new “situation” to change the assumed environment of the invention.

以前にもお話しましたが、やっぱり一番効果があるのは『北朝鮮からのミサイル攻撃』と『南海トラフ地震』ですね。
As I have mentioned before, the most effective ones are “a missile attack from North Korea” and “the Nankai Trough earthquake.”

通信や輸送インフラが破壊された環境で、システムを縮退させつつも、情報を上げ続けるには、どうしたらいいか、という仮想の環境をChatGPTにぶつけると、ChatGPTは、かなり苦しみながらも、それを回避する手段を提示してきます。
When I present ChatGPT with a hypothetical scenario in which communication and transport infrastructure have been destroyed, asking how to keep information flowing while scaling down the system, it struggles but still offers ways to work around it.

ここに発明のネタが潜んでいることが、結構な割合で多いのです ーー で、後は、その背景から、『北朝鮮からのミサイル攻撃』と『南海トラフ地震』という言葉を消して、一般的な状況に戻せば、特許明細書としての設計はおおむね完成、という訳です。
Quite often, an invention idea is hidden in there—and then all I need to do is remove the phrases “missile attack from North Korea” and “Nankai Trough earthquake” and revert it to a general situation. The design for the patent specification is mainly complete.

-----

繰り返しますが、ChatGPTの考えてくるネタの大半は、すでに私または私以外の人が考えていることが多いです。
I repeat, most of the ideas ChatGPT comes up with are ones that I or someone else have already thought of.

ですので、発明の案出そのものには、あまり役に立ちません。
Therefore, it is not particularly useful for generating invention ideas on its own.

ChatGPTの最大のウリは、『私が頭の中で、二人のペルソナ(私(発明者)と私(審査官))をバトルさせる』よりも、圧倒的に短い時間でこのバトルを行えることと、限られた時間の中で何ラウンドも繰り返すことができる、という、その「プロセスの速さや、繰り返し回数の多さ」に尽きます。
The most significant selling point of ChatGPT is that it can conduct this battle in far less time than I running the two personas (inventor-me and examiner-me) in my head, allowing many rounds to be repeated within a limited time—it all comes down to that speed and repeatability of the process.

このプロセスで、私に求められる能力は、(1)ChatGPTが自力で考えつかないトンデモ状況を想定することと、(2)それを思考速度と同レベルで文章にしてChatGPTにぶん投げる、という2つになります。
In this process, the skills I need are to imagine outrageous situations that ChatGPT could never come up with on its own, to turn them into text at the same speed as my thinking, and to present them to ChatGPT.

この2つは、全く"イノベーティブ"な活動ではありません。
These two things are not “innovative” activities at all.

-----

私は、この「トンデモ状況」を考えるのが得意なのですが、これを人間と行うような特許ブレスト(ブレインストーミング)では、しゃべり難いのですよ。
I am good at thinking up these “outrageous situations,” but they are hard to voice in a human brainstorming session.

例えば、
For example—

■「年間300人の子どもが誘拐され、その一割が殺害される社会」(子どもの見守りサービスを考える時の"状況")
※現実の日本の警察統計でも、子どもの誘拐件数は年間数百件規模ですが、殺害率10%は極端に高く、実際よりかなり誇張された数値です。
“300 children kidnapped every year, 10% of whom are killed” (a “situation” when thinking about child monitoring services)
Even in actual Japanese police statistics, the number of child abductions is in the hundreds annually, but a 10% murder rate is extremely high and significantly exaggerated compared to reality.

■「年間5万人の高齢者が意図的に医療から排除され、治療を受けられずに死亡する社会」(高齢者向け在宅医療・ケアサービスを考える時の"状況")
“50,000 elderly people are intentionally excluded from medical care and dying without treatment each year” (a “situation” when thinking about home medical and care services for the elderly)

■「毎年数千人の障害児が、出生直後に行政の判断で収容所に隔離される社会」(障害児と家族の分離防止・支援システムを考える時の"状況")
“Several thousand disabled children are confined to institutions immediately after birth by government decision each year” (a “situation” when thinking about systems to prevent the separation of disabled children from their families)

■「全市民が毎年一度“生存くじ”を引かされ、外れた者は合法的に安楽死させられる社会」(市民の生存権を確保する監視・回避システムを考える時の"状況")
“All citizens required to draw a ‘survival lottery’ once a year, with those losing subjected to legal euthanasia” (a “situation” when thinking about monitoring and avoidance systems to secure citizens’ right to life)

など、私は簡単に思いつくのですが、これを口にすると、ドン引きされて、特許ブレストが"凍る"んですよね。
I can easily come up with these, but the moment I voice them, everyone is taken aback, and the patent brainstorming session “freezes.”

(↑クリックすると、コラムに飛びます)

-----

ともあれ、私の頭の中のブレストはいつも満席です。
So my brainstorming sessions inside my head are always at full capacity.

人間はブレストの参加を拒否しますが、ChatGPTはまだ逃げ出しません。
Humans refuse to join, but ChatGPT hasn’t run away yet.

―― これを"知財搾取"と呼ばずに何と呼ぶ?

2025,江端さんの忘備録

野球もサッカーも、他人がボールを追いかける姿に一切の興味を持てない。
I have absolutely no interest in watching other people chase balls in sports like baseball or soccer.

ギャンブルは、統計的に期待値がマイナスである時点で論外。
Gambling is a non-starter the moment you realize its expected value is statistically negative.

酒を飲んで酔ったふりをしながら、女性に追従を言われる時間など、人生の浪費でしかない。
Pretending to be drunk while being flattered by the opposite sex over drinks feels like nothing but a waste of life.

友人と呼べる存在もおらず、人が集まる場所には反射的に身構える。
I have no one I’d call a friend, and I instinctively tense up in crowded places.

特に「飲み会」という儀式には、もはや嫌悪感すら通り越して諦念を覚える。
As for drinking parties—those social rituals—I’ve moved past disgust into pure resignation.

場を盛り上げる努力を強いられるくらいなら、ひとり自宅で乾ソバをゆがいて麺つゆを作って、すすっているほうがマシ。
If forced to contribute to the party mood, I’d rather stay home, boil some dried soba, make dipping sauce, and slurp in solitude.

人から賞賛を受けても、それを素直に喜ぶ能力が著しく欠如している。
Even when praised, I struggle to accept it with genuine joy.

むしろ、「お世辞」か「下心」の二択だと警戒してしまう。
More often, I interpret it as either flattery or ulterior motives.

達成感もない。充実感もない。帰属意識も、承認欲求も、そして自己肯定感も、ない。
No sense of achievement. No sense of fulfillment. No belonging, no need for validation, not even a shred of self-esteem.

──これは誰か。
Who is this person?

私です。
Me.

-----

昔は、
Once upon a time,

======

しかし、極めて希ではありますが、
Rare though they may be,

テニスやスキーを通じて自己鍛錬に励み、
I refine myself through tennis or skiing,

優れた人格と孤高な精神を有し、
possess outstanding character and a solitary spirit,

高い理想に燃え、
are driven by lofty ideals,

皆から慕われ信頼され、
are admired and trusted by all,

そして、当の本人がその優れた資質に気がついていないことから「歩く人徳」と呼ばれる人物もいます。
and are even called "walking virtue" precisely because they remain unaware of their own excellence.

私です。
That was me.

1997/06/27 江端さんのひとりごと「直撃」

======

って、書いていたんですけどね。
That's what I wrote, back then.

人間っていうのは、変われば変わるものです ―― 本当に。
People change. Truly, they do.

-----

つまり、私は、部屋の中で、コラムか論文か特許か報告書かプログラムを書いていることしかできない人間なんですよ。
Put simply, I’m a person who can only write columns, papers, patents, reports, or code—within the confines of my room.

皆さんが、目くじら立てるようなたいそうな人間ではありません。あまり迷惑かけないつもりなので、静かに放っておいて下さい。
I'm not someone worth fussing over. I intend to bother no one, so please, just leave me be.

それはさておき。
But, that aside—

-----

とは言え、私も「新しい技術」には目がなくて、色々試してみたいという欲望だけは、人一倍あるようです。
That said, I do have a particular weakness for new technology—and an above-average urge to tinker with it.

「推しの技術」という言葉があるかどうかは知りませんが、「推しのアイドル」とか「推しの声優」とか「推しのキャラクター」なんてものと、基本的な構造は同じです。
I don’t know if the term "favorite tech" exists, but structurally, it's no different from having a favorite idol, voice actor, or fictional character.

違うのは、「課金」の方向性です。
The only difference lies in where the money goes.

私は、握手会や、限定グッズや、リアルイベント、聖地巡礼、推し活ノート作成、さらにはライブ配信の投げ銭やアクスタ(アクリルスタンド)収集などには、一円たりとも散財したいとは思いません。
I have zero interest in spending even a single yen on handshake events, limited-edition merchandise, real-life fan gatherings, pilgrimage tours, fan journals, livestream tips, or acrylic stand collections.

けれど、最新の技術書や英語論文のサブスク、実験用クラウド環境や新しいAPIの有料プラン、そして最近では生成AIの有料枠や推論用GPUサーバに対しては、金銭的ブレーキが一気に壊れます。
But when it comes to the latest tech books, English journal subscriptions, experimental cloud environments, paid API plans, and—most recently—premium AI services or inference-ready GPU servers, all my financial brakes come off.

特に、生成AIについては、単なるエンドユーザではなく、技術的な利用を色々試しています。
Especially with generative AI, I’m not just a consumer—I experiment with it on a technical level.

で、先日、GPU付きのPCを購入してしまいました(我が家にあるPCの台数は、もう数えるのも面倒です)。
So, the other day, I bought yet another GPU-equipped PC. I’ve lost count of how many machines I own now.

目的は、ローカルLLMです。
The goal? Running a local LLM.

正確には、ローカルで動作する「マルチモーダル生成AI」ですが、ここでは便宜上「ローカルLLM」と呼ぶことにします。
Strictly speaking, it's a locally-run multimodal generative AI—but for simplicity, let’s just call it a local LLM.

ローカルLLMとは、インターネットに接続せずに、自宅のPCだけで大規模言語モデル(LLM:Large Language Model)を動かすことができる仕組みです。
A local LLM is a system that runs a large language model entirely on your home PC, without requiring an internet connection.

簡単に言えば、「ChatGPTっぽいものを、自分のPCの中で自前で動かしてしまおう」という話です。
Put simply, it’s about running a ChatGPT-like model privately on your own hardware.

通信遮断されたオフライン環境でも、誰にも履歴を覗かれず、誰の検閲も受けず、ひたすら自己完結的に対話できる。
Even in a fully offline environment—no prying eyes, no censorship—you can hold conversations in total solitude.

もちろん、OpenAIのような商用サービスを使えばもっと手軽にLLMを使えますが、それでは通信環境や料金体系、データの秘匿性の面で不安が残ります。
Sure, you can use commercial services like OpenAI’s for convenience—but there are always concerns: internet access, pricing structures, data privacy.

私のような「自分の部屋の中で全て完結させたい人間」にとっては、ローカルLLMはまさに「理想の相棒」と言えるものなのです。
For someone like me—who wants everything to stay within the confines of their room—a local LLM is the perfect companion.

-----

で、昨日、ChatGPTの支援を受けながら、映像の内容を「説明」するローカルLLMの構築を、購入したPCに実装していました。
Yesterday, with the help of ChatGPT, I implemented a local LLM that can describe visual content—right on the newly built PC.

画像用LLMの立ち上げ方

ある写真をプログラムに読み込ませたら、一発で、
I fed it a single photo, and right away, it returned:

「毛皮の上に乗っている、青い目をしたネコ」
"A blue-eyed cat sitting on a fur blanket."

と説明を返してきました。
Just like that.

-----

外の世界との接点が、ますます必要なくなっていく実感があります。
I can feel my need for the outside world gradually fading.

技術は、私を助けると同時に、世界から切り離していく存在でもあるのです。
Technology, while supporting me, is also quietly isolating me from the world.

インターネットすらも不要として、「ローカルLLM」と共に生きて、そして、死んでいく ーー そういう『究極のひきこもり』は、もう始まっています。
The age of the “ultimate shut-in”—living and eventually dying alongside a perfect companion that doesn’t even require the internet—has already begun.

2025,江端さんの忘備録

他人が書いたプログラムを読むことは、たいていの場合「不快」です。
Reading code written by someone else is, in most cases, simply unpleasant.

コードの向こうにある「他人の脳を切り開いて覗く」ような感覚があるからです。
It feels like prying open someone else's brain and peering inside through their code.

「なぜ、ここでこんな書き方を?」といった疑問や、「そんな命名ありか?」という苛立ちが、読む側の心を削っていきます。
Questions like “Why would they write it like this?” or frustrations like “Who names variables this way?” slowly wear down your soul.

それでも、他人の書いたプログラムを読まなければならない場面は確かにあります。
Still, there are times when you must read other people's code.

業務である以上、そんなことに好き嫌いを言っていられません。仕事ですから、読んで理解するしかないのです。
Since it's work, personal preferences don't matter. I just have to read it and understand it.

まあ、ここまでは普通の業務の話です。
Up to this point, it's all fairly standard workplace reality.

-----

厄介なのは、「これは別に読まなくていいよ」とアドバイスされた言われたコードです。
The real trouble begins with code I am explicitly told not to read.

読む必要がないと明言されているにもかかわらず、結局のところ、私はコードを読んでいます。
Even though I’ve been clearly told it’s unnecessary, I end up reading it anyway.

なぜなら、全体のシステムを把握するには、細部を知っておく必要があるからです。
Because in order to grasp the system as a whole, I need to understand the details.

中身が分からなければ、構造をイメージできません。
If I don’t know what’s inside, I can’t mentally picture the structure.

イメージができなければ、システム全体を設計・構築することは困難です。
And if I can’t visualize it, designing or building the entire system becomes extremely difficult.

まあ、できる人もいるのかもしれませんが、私は、コーディングの技術レベルが低いのです(謙遜ではなくて、弊社で働いていれば思い知らされます)。
Perhaps some people can pull it off, but to be honest, my coding skills are not that high (and no, this isn’t modesty, but working at my company will quickly make that reality clear).

-----

そして結局、「なるほど、確かにこれは読まなくてよかったな」と、"読んだ後"に"後悔する"ことになります。
And in the end, I regret reading it saying to myself, “Yep, I really didn’t need to read this after all.”

つまり、「読む必要がない」ことを理解するために「読む」という、実に奇妙なループに陥るのです。
In other words, I fall into the bizarre loop of reading code just to understand that I didn’t need to read it.

そして、今後も、私は、このような、生産性のない「奇妙なループ」を回し続けると思います。
And I suspect I’ll keep repeating this kind of unproductive loop again and again in the future.

そのことについて"だけ"は、自信があります。
That’s the one thing I can say with absolute confidence.

-----

ただ、こうした理不尽は、なにもプログラムの世界に限った話ではありません。
But this kind of absurdity isn’t limited to programming.

たとえば、「お前は、お金のことなんか心配せずに勉強だけしていればいい」といった保護者のアドバイスがあります。
For example, parents often say things like, “You just focus on studying; don’t worry about money.”

あるいは、「気にしないで自由にやりなさい」とか、「考えすぎだよ」といった言葉もよく聞きます。
Or, “Just do what you want,” or “You’re overthinking it.” Those are common, too.

言っている側は相手を思っているのでしょうが、それは相手の本当の気持ちを理解しているとは限りません。
The speaker likely means well, but that doesn’t mean they understand how the other person truly feels.

------

『俺は分かってもらいたいんじゃない。俺は分かりたいのだ。分かりたい、知っていたい、知って安心したい、安らぎを得ていたい。分からないことはひどくこわいことだから(やはり俺の青春ラブコメは間違っている 第2期8話)』
“It’s not that I want to be understood. I want to understand. I want to know, I want to be informed, I want peace of mind, I want to feel at ease. Not knowing is terrifying.” (My Teen Romantic Comedy, as expected, Season 2, Episode 8)

このアニメのセリフのように、人は「分かること」で安心を得る生き物です。
Like this anime quote suggests, humans find peace in understanding.

「分からなくてもいい」では済まされない不安があるのです。たとえ読む必要がないと言われても、それを確かめるために読む。たとえ説明されていても、自分の目で確かめたい。
Being told “You don’t need to understand” just doesn’t cut it. We read to verify it ourselves. Even if it’s explained, we want to see it with our own eyes.

これは、ロジックの話ではなく感情の話です。
This isn’t about logic but about emotion.

プログラムであれ、人生であれ、「分からないこと」は、怖いのです。
Whether it’s code or life, not understanding something is just plain scary.

------

私の人生を業(カルマ)的に語れば、
If I were to describe my life in terms of karma,

(1)「読まなくていい」と言われたコードを読んで後悔するか、
(1) I either read the code I was told not to, and regret it,

(2)「読まずにやって壊して怒られる」か
(2) or I don’t read it, break something, and get scolded.

だいたいこの二択です。
Those are, for the most part, the only two options.

そして今日も、私は前者で消耗しています。
And today, once again, I’m drained from choosing the first.

―― 斬新な"虐待"だなぁ

2025,江端さんの忘備録

チケットの転売が社会問題になっています。
Ticket reselling has become a social issue.

社内で開催される講演会の出席率の低さが(以下、自主規制)。
The low attendance rate at internal company lectures is... (self-censored).

社内講演会は業務時間中に開催されるため、出席しても問題はありません。
Internal lectures are held during working hours, so there's no problem in attending them.

ただし、この「業務時間内」というのがクセモノです。
However, the phrase “during working hours” is somewhat ambiguous.

はっきり言って、みんな「忙しい」。
Everyone is “busy.”

講演を聞きたくても、時間がないのです。
Even if they want to attend the lecture, they don’t have the time.

リモート中継で済む話では?と思いがちですが、
You might think a remote broadcast would solve the problem,

主催者側としては「リアルな出席人数」が大きな評価ポイントになるようです。
But for the organizers, the number of people physically present is often a key metric.

-----

その気持ち、私にはよく分かります。
I completely understand that sentiment.

出席者が少ないと、
When there are few attendees,

せっかく講演を依頼した大学の先生や著名な著者に対して「申し訳ない」という気持ちが湧いてくるでしょう。
You can’t help but feel “sorry” toward the professor or distinguished author you invited.

さらに、質疑応答が盛り上がらないと、
Moreover, if the Q&A session doesn’t take off,

「関心がなかったのでは?」という無言のメッセージになってしまうのでは、という心配もあるでしょう。
You worry it sends a silent message: “Maybe people weren’t interested.”

-----

私が主催者だった頃は、
When I was the organizer,

「この先生の◯◯の話が最高!」「この本は何度も読んだ、面白かった!」など、
I would write things like “This professor’s talk on XX is amazing!” or “I’ve read this book multiple times—it's great!”

ネタバレすれすれの宣伝文を、
—almost spoiler-level promotional messages—

メール(当時はチャットもSNSもなかった)で、言葉を変えながら繰り返し発信していました。
I would keep sending them emails (there was no chat or social media at the time), changing the wording each time.

要するに、「コンテンツの中身」を「自分の言葉」で伝える努力をしていました。
In short, I made the effort to convey the “content” in “my own words.”

(今にして思えば、かなりの時間をかけていました)。
(Looking back now, I realize I spent a lot of time on it.)

そんな過去をもつ主催者の一人としては、
As someone with that kind of experience as an organizer,

「業務命令による強制動員」は、ちょっと違うんじゃないかな?という気がしています。
I can’t help but feel that “mandatory attendance via work orders” is somehow... off.

ただ、講演を依頼した相手との関係などを考えると、
That said, considering the relationship with the invited speaker,

ある程度の「業務命令」もやむを得ないのかもしれません。
Some level of “work-enforced attendance” might be inevitable.

-----

私も、学会での発表で聴講者が少ないとガッカリすることはあります。
I also feel disappointed when there are few attendees at my conference presentations.

せっかくなら聞いてほしい。資料作成もがんばったので。
After all, I want people to hear it, and I worked hard on preparing the materials.

私の場合、なぜか聴講者が少なくても質問が多いです。
In my case, for some reason, even with a small audience, I get a lot of questions.

私自身も聴講したら必ず1つは質問するようにしています。
I always ask at least one question when I attend a lecture.

-----

逆のケースもあります。
But there’s also a case where the opposite is true.

たとえば、論文の最終審査(公聴会)では、出席者は少ない方がありがたい。
For example, in the final thesis defense (public hearing), fewer attendees are welcome.

なぜか?
Why?

論文最終審査とは、英語で「Final Defence」って言うんですが ----
Because in English, the final thesis presentation is called a “Final Defence”—

真の意味において「専守防衛」なんです(この話はまた別の機会に)
In the truest sense, it’s “strictly defensive warfare.” (More on that another time.)

-----

本日の結論としては、講演の出席率を上げたいなら「業務命令」より「ネタバレ」です。
In conclusion, if you want to boost attendance, “spoilers” work better than “work orders.”

あと、ケーキやビールも効果あります(たぶん)。
Additionally, cake and beer are also helpful. (Probably.)

『英語に愛されないエンジニアの、国際学会プレゼンテーションのリアル』

2025,江端さんの忘備録

私たちは、基本的に「やりたいこと」や「好きなこと」など持っておらず、日常の中で行われた行動の中で、比較的『気分がよかったこと』を、「やりたいこと」や「好きなこと」に置き換えているだけ──
We, in essence, don't have things we “want to do” or “like to do.” Instead, we tend to label actions that happened to feel relatively pleasant in our daily lives as our “wants” or “likes.”

という話は、何度もしてきました。
This is something I’ve talked about many times before.

もし、上記の私の説が"真"であったとすると、他人に対して「好きなことをしなさい」というのは、結構な『虐待』だと思うのですよ。
If my theory above is true, then telling someone to “do what you like” is a rather cruel form of emotional abuse.

「好きなことをしなさい」を、上記の私の定義に当てはめれば、
If we apply my definition to the phrase “do what you like,”

「“ない”をしなさい」→「何もするな」となる訳です。
It turns into “do what doesn’t exist” → essentially “do nothing.”

これは、 本当に酷い言い草です。
That’s an incredibly harsh thing to say.

-----

「好きなことをしなさい」とか"言うだけ"の保護者は、子どもに対してネグレクトをしていると思っています。
I think parents who say “do what you like” without offering any further guidance are essentially neglecting their children.

分かりますよ。自分のことだけで精一杯の毎日において、子どもであろうとも、他人のことを考えるのって、面倒です。しかも、子どもの将来がかかっているとなれば、責任も発生します。
I get it. In a life where you're barely keeping up with your own needs, it's a hassle to think about others—even if that “other” is your child. And if it involves their future, it also comes with a heavy sense of responsibility.

そういうことから逃げたいと思う保護者がいたとしても、それは仕方がない、とも思います。
So, if a parent wants to run from that kind of pressure, I can’t entirely blame them.

そのようなネグレクトではなくとも、「自分の意見が子どもの自主性を損うかもしれない」と、心配する人もいるかもしれません。
Even apart from neglect, there may be those who hesitate because they worry that offering their own opinion might damage their child’s autonomy.

で、まあ、実際のところ、多くの保護者は「とりあえず大学に行っておけ」という、『問題先送り』を行う訳です──まあ、これはこれで、戦略としては悪くはない。
So then, in practice, many parents end up saying, “Just go to college for now”—a classic case of kicking the can down the road. And honestly, as a strategy, it’s not necessarily a bad one.

問題を先送った先にいる子どもは、すでに法定における成人です。「成人であれば、自己決定ができなければならない」というセリフで、無事、子どもに対する責任を回避したまま逃げきれることになります。
By the time the issue reappears, the child is already a legal adult. Then you can say, “Adults should be able to make their own decisions,” and neatly dodge any lingering responsibility.

-----

で、まあ、こんな批判は、世の中に腐るほどあるので、私はユースケースで示してみたいと思います。登場するのは、今回もChatGPTです。
Criticism like this is everywhere, so instead, I’d like to present a use case. Once again, our subject is ChatGPT.

子どもの意見を、こういう形で、子どもの声をChatGPTに入力するくらいのことなら、できると思います。
At the very least, typing your child’s thoughts into ChatGPT—this much is something any parent can do.

これなら、あなたでも、子どもに寄り添った方向でアドバイスができるようになるかもしれません(まあ、考えたのは、あなたではなくてChatGPTですけど)。
With this, you may even be able to offer advice that’s in tune with your child’s needs. (Though let’s be honest—it's not your advice. It's ChatGPT’s.)

===== ChatGPTとの会話 ここから =====
===== Conversation with ChatGPT Begins =====

私は教科書にイラストの落書きを書くのが好きですが、漫画家になるほどのストーリーの組み立てができる訳でもありませんし、絵を業務とするクリエーターになろうという気合もありません。成績は卒業できるかどうかの低レベルです。親は「やりたいことをやりなさい」と言いますが、私には「やりたいことが分かりません」。こんな私の進路について、夢のような話ではなく、現実的に実現可能な範囲の進路について、アドバイスをして下さい
I like doodling illustrations in my textbooks, but I don’t have the ability to build up stories like a manga artist, nor do I have the ambition to become a professional illustrator. My academic performance is low, barely enough to graduate. My parents say, “Do what you want to do,” but I don’t know what I want. Please give me advice on a career path that is not a fantasy, but realistically achievable.

あなたのように「好きなことはあるけれど、明確な夢や職業目標は持っていない」という人は、実はとても多いです。そして、それは「ダメなこと」でも「劣っていること」でもありません。むしろ、自分を冷静に見ている証拠です。
There are many people like you—people who have things they enjoy, but don’t have a clear dream or career goal. And that’s neither a bad thing nor a weakness. It’s a sign that you’re looking at yourself with a cool head.

あなたの状況に対して、夢物語ではなく、地に足のついた進路の選び方を、以下の3つの方向性で提案します。
Based on your situation, here are three grounded directions for you to consider—realistic, not fantasy-based.

1. 「描くこと」を副業または趣味で続けながら働く道
1. Keep drawing as a hobby or side job while working

現実的な進路:
Practical career options:

  • 事務職、販売職、軽作業、介護補助など、安定して働ける職種に就く
    Work in stable jobs such as office work, retail, light labor, or caregiver assistance

  • そのうえで、趣味としてイラストを描き続ける(SNS投稿、同人誌、LINEスタンプなど)
    Continue drawing as a hobby—posting on social media, creating doujinshi, or making LINE stickers

理由:
Why this works:

  • 漫画家やプロイラストレーターにならなくても、描くことはやめなくていい
    You don’t need to become a manga artist or professional illustrator to keep drawing

  • 好きなことを「手放さずに生きる」ことも立派な選択
    Living without letting go of what you love is a valid life choice

  • 副業で小さく始めて、もし反応が良ければ将来拡大も可能
    If you get a good response, you can gradually expand into side gigs or more


2. 「美術的センス」を活かせる裏方の仕事を目指す
2. Aim for behind-the-scenes jobs that use your artistic sense

現実的な進路:
Practical career options:

  • 印刷会社、デザイン補助、看板屋、POP制作、ネットショップ運営補助
    Work at a print company, assist in design work, signage creation, point-of-purchase displays, or help manage online shops.

  • 専門学校で短期間のDTP(印刷物制作)やデザイン技術を学ぶのも選択肢
    Consider short-term vocational school training in DTP (desktop publishing) or design skills

理由:
Why this works:

  • 自分で創作しなくても「見る目」「構成力」は役に立つ
    Even if you don’t create, having an eye for design and composition is valuable.

  • ストーリーを作れなくても、素材をまとめる仕事はある
    You don’t need to write stories—there are jobs focused on assembling materials

  • デザイン補助なら高スキルは不要でも歓迎される現場が多い
    Many workplaces welcome design assistants without needing top-tier skills


3. とにかく働きながら、好きなことを試し続ける道
3. Keep working while trying out different interests

現実的な進路:
Practical career options:

  • まずは卒業を目標にして、バイト→正社員化が見込める職場で経験
    First, aim to graduate. Then work part-time at a job with potential to become full-time

  • 並行して、「自分が嫌いじゃないこと」を少しずつ試す
    Alongside, try out things you don’t dislike—bit by bit

    • 絵以外でも「興味がなくはない」ことを試す(動画編集、接客、パソコン作業など)
      Try things beyond drawing—like video editing, customer service, or computer work

理由:
Why this works:

  • やりたいことは「考えて分かるもの」ではなく「試して分かるもの」
    You don’t figure out what you want to do by thinking—you find it by trying

  • 最初の仕事が「一生の仕事」になる必要はない
    Your first job doesn’t need to be your lifelong career

  • 一つの仕事を1~2年やってみることで、自分の向き不向きがわかる
    Doing a job for 1–2 years will help you understand your strengths and weaknesses


最後に一言:
Final Thought:

「やりたいことが分からない」状態のまま、人生を進めても大丈夫です。
It’s okay to move forward in life even if you don’t know what you want to do.
むしろ、「分からないけど動き続けた人」の方が、あとから本当にやりたいことに出会います。
In fact, those who keep going despite not knowing often end up discovering what they truly want to do later on.

あなたが「落書きが好き」という感覚を見つけられているのは、とても貴重です。それは「無い」ではなく、「小さな種」をもう持っているということです。その種を、生活のどこかで大事に育てながら、まずは現実に食べていける進路を一緒に探していけばいいのです。応援しています。
The fact that you’ve found joy in doodling is precious. That’s not “nothing”—you already have a small seed. Take care of that seed somewhere in your life, and in the meantime, let’s find a career path that helps you earn a living. I’m rooting for you.

===== ChatGPTとの会話 ここまで =====
===== End of Conversation with ChatGPT =====

あなたに必要なのは「考えること」ではなく、「子どもの意見をまとめてChatGPTに入力する作業」なのです。
What you need isn’t to think—it’s to gather your child’s thoughts and input them into ChatGPT.

これも「ネグレクト」の一態様かもしれませんが、子どもに「好きなことをしなさい」と言うより、はるかに「マシ」です。
This might also be considered a form of neglect. But compared to telling your child to “do what you like,” it’s a far better option.

-----

ChatGPTの答えは、完璧でも万能でもありません。でも、子どもの「困っている気持ち」に対して、「一緒に困ること」ができます。そして、それで十分で、それが一番大切だと、私は思っています。
ChatGPT’s answers aren’t perfect or all-knowing. But it can help you share in your child’s confusion—and that, in itself, is enough. I believe that’s the most important thing of all.

―― 私たちには、やりたいことなどない

2025,江端さんの忘備録

昨日、マンホールで作業中の人が4人死亡するという、痛ましい事故が発生しました。
Yesterday, a tragic accident occurred in which four workers died while working inside a maintenance hole.

事故理由は現在調査中のようですが、マンホールに滞留していた硫化水素(150ppm)が原因として疑われているようです。
The cause of the accident is still under investigation, but it appears that hydrogen sulfide (150ppm) accumulated in the maintenance hole is suspected to be the cause.

硫化水素の濃度と人体への影響を調べてみたのですが、「150ppm嗅覚の麻痺(臭いが感じられなくなる)→10分程度で失神→1時間で死亡」と記載されていました。正直、今、背筋が凍っています。
I looked into the concentration of hydrogen sulfide and its effects on the human body.  "At 150 ppm, olfactory paralysis occurs (you can no longer smell it) → unconsciousness in about 10 minutes was what I found written. Honestly, I feel a chill down my spine.

-----

私、この手の有毒ガスによる事故については、これまで何度か悲しい目にも、危ない目にも遭遇しました。
I have personally encountered several sorrowful and dangerous incidents involving accidents caused by toxic gases like this.

こういう、危険な気体は、実は私たちの身の回りにたくさんあります。
Disasters caused by hazardous gases like these are a part of everyday life.

私たちでは対処しきれないこともあるとは思いますが、少なくとも以下のような私が引き起こした愚かな事故くらいであれば、「基本的な知識」と「日常的な常識」で回避できます。
There may be situations beyond our control, but at the very least, foolish accidents like the one I caused can be avoided with basic knowledge and everyday common sense.

江端さんのひとりごと 「危ない漂白剤」

どうか、お命安全で、お過ごしください。
Please, stay safe and protect your life.

-----

P.S.

ちなみに、上記のコラムに記載していた「次亜塩素酸ナトリウム」は物質であり気体ではありませんし、その他にも、各種の誤記や誤解が大量にあると思っていました。以前から、この記載の誤っている点を全部チェックしたいと思っていたので、今回ChatGPTに教えて貰いました。

=====

このエッセイには、科学的・化学的な誤解や不正確な記述が複数あります。以下に、科学的・化学的に誤っている記述を明示し、それぞれに対して何が誤っているか/正しい知識を併記します。


❌ 科学的・化学的に誤っている記載一覧


①「漂白剤を煮立てれば、すごく速くコップの漂白できるのでは」

  • 誤りの内容:漂白液(主成分:次亜塩素酸ナトリウム)を加熱すれば漂白が早くなるという前提。

  • 正確な知識
    加熱により漂白効果が一時的に高まる場合はありますが、次亜塩素酸ナトリウムは熱に不安定で、加熱により急速に分解し、逆に効果が失われます。

  • 副作用:同時に酸素や塩素ガスが少量ながら発生する危険性があり、漂白目的での加熱は推奨されません


②「2分もないうちに、あのプール独特の塩素の匂いが部屋中に立ちこめてきた」

  • 誤りの内容:「塩素の匂い」と表現しているが、プール臭の主因はCl₂ではない。

  • 正確な知識
    プールや漂白剤の匂いの主成分はクロラミン類(モノクロラミン NH₂Clなど)であり、塩素ガス(Cl₂)とは別物です。Cl₂が漂白液から単独で発生するには強酸との反応が必要です。

  • 補足:煮立てただけでは塩素ガスは大量には出ませんが、**塩素臭に似たもの(次亜塩素酸などの刺激臭)**が出ることはあります。


③「しまった!次亜塩素酸ナトリウム!!…煮沸なんかしたら、この部屋は実に理想的なガス室と化してしまいます」

  • 誤りの内容:煮沸によって、ナチスが使用したような致死的ガス(例:シアン化水素など)と同等の毒性が発生するという認識。

  • 正確な知識
    次亜塩素酸ナトリウムを煮沸しても、ナチスの用いた「チクロンB(シアン化水素 HCN)」とは全く別物です。
    加熱により酸素や少量の塩素、クロラミンなどが発生する可能性はあるが、密室でなければ即死レベルには達しにくい

  • 懸念:危険性を過小評価するのは危険だが、過剰に「ガス室」と同一視するのも科学的には誤り


④「水道水にも使われている有毒ガス」

  • 誤りの内容:次亜塩素酸ナトリウム=有毒ガスという表現。

  • 正確な知識
    水道水に使われているのはごく微量の次亜塩素酸ナトリウムであり、そのまま飲んでも人体にほとんど影響はない濃度に調整されています。

  • 補足:原液や高濃度溶液は危険だが、水道水レベルで「有毒ガス」と言うのはミスリーディングです。


⑤「コップごと煮る」=金属の腐食・反応のリスクに未言及

  • 誤りの内容:金属製コップで加熱した漂白液による二次反応の可能性に無自覚。

  • 正確な知識
    金属(特にアルミ・鉄・銅など)と次亜塩素酸ナトリウムが反応すると、クロラミンや酸素、酸化物などの副生成物が発生することがあり、発泡や腐食、刺激臭などの危険を伴う

  • 補足:ステンレスなら比較的安定だが、鉄製コップでの加熱はリスクが高い


✅ 科学的に正しいポイント(補足)

  • 頭痛・息苦しさなどの症状は、加熱によるガス(塩素やクロラミンなど)への曝露で説明可能です。

  • 室内の換気が不十分な状態で、化学物質を加熱する行為は実際に非常に危険です。


🔚 結論:このエッセイでの科学的な誤認一覧まとめ

誤認ポイント 内容 正しい知識・修正方向
① 加熱で漂白力UP 一時的に効果上がるが分解進行で逆効果も 加熱は避けるべき
② プール臭=塩素 クロラミン類が主原因 塩素ガスではない
③ 「ガス室」化する ナチス使用の毒ガスと混同 毒性はあるが別物
④ 水道水に有毒ガス 超微量で無害、濃度誤解 適切な濃度管理下では安全
⑤ 金属との反応未考慮 鉄と次亜塩素酸の反応に無自覚 腐食や有毒ガス発生のリスクあり

=====

以上

2025,江端さんの忘備録

私は現在禁酒中の身の上ですが、(だからこそ?)漫画「グランブル(*)」の大ファンであることは以前お話しました。
I’m currently abstaining from alcohol, but (perhaps because of that?) I’ve previously mentioned that I’m a big fan of the manga “Grand Blue.”

(*)「ぐらんぶる」(英語タイトル:Grand?Blue Dreaming)は、講談社の青年漫画誌「good!アフタヌーン」にて、2014年5月号から連載されている作品(原作:井上堅二さん/作画:吉岡公威さん)です。
(*) “Grand Blue” (official English title: Grand Blue Dreaming) has been serialized since the May 2014 issue in Kodansha’s seinen manga magazine good! Afternoon (original story by Kenji Inoue, art by Kimitake Yoshioka).

多くの人が意外に思われるかもしれませんが、私は、井上堅二さん(原作)と吉岡公威さん(作画)の「ぐらんぶる」という漫画/アニメが大好きです。

-----

で、今回は、いわゆる、"コレ"の内容の話が掲載されていました。
And this time, it featured a story about what you might call “that thing.”

江端さんのひとりごと「危ない炊飯器」

―― 私の場合、1月後の炊飯器は確かに“こういう状態”だった
In my case, the rice cooker did indeed end up “just like that” one month later.

―― しかし、2年も経過すれば「宇宙の熱量死」に至っているハズなんだけどな
But after two years, surely it should’ve reached the “heat death of the universe,” no?

と、私は、首をかしげていました。
So I found myself tilting my head in puzzlement.

-----

私のこのコラムに対する感想を調べたことがあるのですが、「炊飯器の中の閉じた宇宙」の事故の話は、結構多いようです。
Well, I once looked up reactions to that column, and it turns out there are quite a few stories about “a closed universe inside the rice cooker.”

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")

 

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』――