江端さんの忘備録(2020/05/05分から)

2025,江端さんの忘備録

先日、こちらの日記で、「このバルチック艦隊に日本海軍が仕掛けた、秋山真之の立案した戦法というのが、未だに、よく理解できていません」と記載しました。

The other day, in this diary, I wrote, “I still don't understand the battle plan that the Japanese Navy devised for the Baltic Fleet, which Akiyama Masayuki proposed.”

「坂の上の雲」の再放送を見てみると、日露戦争において、我が国は、奇跡的なラッキーを5つぐらい連続で掴むという、歴史的幸運に恵まれていたことを思い知ります。

で、先週、このシーンが放送されました。

So, this scene was broadcast last week.

私は、エンジニアで、研究員で、SE(システムエンジニア)で、ネットワーク技術者ですが、やはり一番しっくりくるのが『シミュレーション屋』です。

I am an engineer, researcher, system engineer, and network engineer, but I think the term best describes me is “simulation engineer.”

そういう、シミュレーション屋の性(さが)として、『秋山真之の立案した戦法というのが、未だに、よく理解できていません』というのは沽券に係わります(いや、正直、そうでもないんですが)。

As is the nature of simulationists, it is a matter of honor (well, to be honest, it's not really that important) to say, 'I still don't understand the battle plan that Akiyama Manayuki came up with.

で、前回の放送で、どうしても手に入れたかった情報である、日本海軍とバルチック艦隊の位置と時間の情報(海図)を、テレビの画面をスマホで撮影して、そこから分析してみました。

So, in the previous broadcast, I took a photo of the TV screen with my smartphone and analyzed the information (Nautical chart) on the location and time of the Japanese Navy and the Baltic Fleet, which I wanted to get.

ようやく分かってきた「秋山真之」の"T字戦略"

で、先程、この答合わせを、ChatGPTにしてみました。

So, I tried using ChatGPT to check my answers.

添付の画像に示すように、まず日本艦隊がUターンを行うことで、ロシア艦隊の砲撃をさそう形で1列に並べて、そして、その1列にならんだロシア艦隊の前に、先んじて立ち塞がり、列で進行してくるロシア艦隊を正面から逐次撃破した、という風に理解したのですが、これは正しいでしょうか

As shown in the attached image, I understood that the Japanese fleet first made a U-turn, lined up in a single row to lure the Russian fleet into firing on them, and then stood in front of the Russian fleet, which was lined up in a row, and defeated the Russian fleet, which was advancing in a line, one after another from the front. Is this correct?

===== ChatGPT回答ここから =====

はい、おおむね正しい理解です。

戦術の流れ

  1. 東郷ターン(Uターン)で敵砲撃を誘発

    • 画像の右側(青線)を見ると、日本艦隊が大きくUターンしていることが分かります。これは**「東郷ターン」**と呼ばれるもので、日本艦隊はこの動きによって、ロシア艦隊の砲撃を一時的に分散させる形になります。
    • この機動によって、日本艦隊はロシア艦隊に対して相対的に有利な位置を取ることが可能になります。
  2. ロシア艦隊を1列に誘導

    • バルチック艦隊(ロシア艦隊)は南下しながら戦列を維持しているため、先頭艦が攻撃を受けると、それに続く艦も回避行動が難しくなるという弱点を持っています。
    • 日本艦隊の機動によって、ロシア艦隊の進行方向を制限し、1列に並ばざるを得ない形に誘導されました。
  3. 「T字戦法」による迎撃

    • 日本艦隊はロシア艦隊の進行方向の正面を塞ぐ形で横向きに展開し、T字を形成しました。
    • この位置関係では、日本艦隊は側砲(舷側砲)を最大限に活用できるのに対し、ロシア艦隊は前方の主砲しか使えず、不利な状況に陥る
    • 画像でも、日本艦隊の砲撃が集中してロシア艦隊の先頭艦を撃破し、敵の進行を阻害している様子が描かれています(赤線の砲撃)。
  4. 逐次撃破

    • 先頭のロシア艦が撃沈または大破すると、その後続艦は回避行動を取らざるを得ず、戦列が乱れます。
    • これによって、ロシア艦隊は組織的な反撃が難しくなり、日本艦隊は効果的に逐次撃破を行うことができました。

結論

あなたの理解は概ね正しいです。「東郷ターン」を使って敵の砲撃を誘い、T字戦法を完成させ、逐次撃破を行うという流れになっています。特に、ロシア艦隊の隊列を分断することに成功した点が、日本海海戦の勝因の一つです。

===== ChatGPT回答ここまで =====

Here is the complete translation of your requested text while keeping the content and format unchanged.


Akiyama Saneyuki’s "T-Shaped Tactics" in Detail

Akiyama Saneyuki’s "T-Shaped Tactics" (丁字戦法, T-jisenpō) refers to the naval strategy employed by the Imperial Japanese Navy to engage the Russian Baltic Fleet during the Russo-Japanese War (1904-1905). This strategy was notably executed in the Battle of Tsushima (May 27-28, 1905), which played a decisive role in Japan’s overwhelming victory.

1. Basic Concept of the T-Shaped Tactics

The T-shaped tactics involved positioning the fleet to form the horizontal bar of the letter "T" relative to the enemy fleet’s line of advance. This had several key advantages:

  • Maximizing the firepower of the Japanese fleet by enabling broadside attacks.
  • Focusing concentrated fire on the leading enemy ships, disrupting their formation.
  • Obstructing the enemy’s route, restricting their maneuverability.

2. Execution of the T-Shaped Tactics in the Battle of Tsushima

Akiyama Saneyuki, as the chief strategist for Admiral Tōgō Heihachirō, devised and implemented this strategy in the battle. The execution proceeded as follows:

1. Detecting the Russian Fleet in Advance

  • The Japanese navy deployed scout ships in advance to track the movements of the Baltic Fleet.
  • The Russian fleet’s passage through the Tsushima Strait was confirmed, allowing for a well-planned interception.

2. Execution of the "Tōgō Turn" to Establish the T-Shaped Formation

  • On May 27, 1905, the Japanese fleet altered its course to intercept the enemy.
  • Admiral Tōgō led the fleet in executing the "Tōgō Turn," a dramatic U-turn maneuver designed to position the Japanese fleet across the enemy’s path.
  • As a result, the Japanese fleet’s leading battleships lined up perpendicularly to the Russian fleet’s advance, forming a "T" shape.
  • This allowed Japan to use its full firepower while limiting the Russians’ ability to return fire effectively.

3. Decisive Destruction of the Russian Fleet

  • The Japanese fleet unleashed concentrated artillery fire, critically damaging the Russian flagship "Suvorov" and other lead ships.
  • This disrupted the command structure of the Russian fleet, throwing it into confusion.
  • As a result, most of the Russian fleet was sunk, captured, or forced to surrender, securing a resounding Japanese victory.

3. Significance of the T-Shaped Tactics

The success of this strategy demonstrated a significant evolution in naval warfare tactics, with several key takeaways:

  • Proof that superior tactics could defeat a numerically superior enemy

    • Although the Russian fleet had more significant numbers and firepower on paper, it was decisively beaten by superior maneuvering.
  • Highlighting the importance of positioning in naval combat

    • Previously, raw firepower and armor were considered the primary determinants of naval battles. However, this battle proved that strategic positioning could dictate the outcome.
  • Emphasizing the role of strategic planning

    • Akiyama Saneyuki’s planning, combined with Tōgō’s decisive execution, demonstrated that a well-planned strategy could dramatically alter the balance of power in a battle.

4. Evaluation and Limitations of the T-Shaped Tactics

While highly effective in the Battle of Tsushima, the T-shaped tactics were not universally applicable, and their effectiveness had limitations.

Advantages

  • Allowed for maximum firepower concentration against the enemy.
  • Restricted the enemy’s ability to maneuver and return fire.

Disadvantages

  • Required precise timing and an accurate prediction of enemy movements.
  • Lost effectiveness if the enemy changed formation in response.
  • Became less relevant with advancements in naval warfare, particularly with the introduction of aircraft and submarines.

Following World War I, the rise of new naval technologies gradually reduced the effectiveness of such large-scale fleet engagements, making the T-shaped tactics less relevant in modern warfare. However, they remain an essential case study in naval strategy.

5. Conclusion

Akiyama Saneyuki’s T-shaped tactics were a groundbreaking strategy that led to Japan’s decisive victory in the Battle of Tsushima. Japan maximized its firepower by predicting enemy movements and optimizing its fleet positioning while minimizing enemy retaliation. While this strategy became obsolete with technological advancements, it remains one of the most studied naval tactics in history and a testament to the importance of strategic planning in warfare.

私の解釈に間違いがあるとすれば、どこになりますか?

If there is a mistake in my interpretation, where would it be?

===== ChatGPT回答ここから =====

あなたの解釈はほぼ正しいですが、厳密に言えば、「正面から逐次撃破した」という点が完全に正しいとは言えない部分があります。具体的にどこが違うのか、詳しく説明します。


1. 「正面から撃破した」という表現の修正

あなたの解釈では、「ロシア艦隊が1列に並んだ状態で、それを日本艦隊が正面から迎え撃ち、順番に撃破していった」というように見えます。しかし、実際には次のような違いがあります。

日本艦隊の射撃方向

  • 「正面から」ではなく「側面から」撃破していったのが正しい。
  • 日本艦隊はロシア艦隊の進行方向を塞ぐ形で展開し、T字戦法を完成させた。
  • この位置関係では、日本艦隊は側面砲(舷側砲)を最大限に活用できるが、ロシア艦隊は前方の主砲しか使えないため不利だった
  • そのため、実際には「日本艦隊が横から砲撃し、ロシア艦隊の先頭から撃破していった」というのが正しい。

あなたの解釈では「正面からの撃破」となっているが、実際には「横からの撃破」だった点が異なる。


2. 「東郷ターン」は敵の砲撃を誘ったか?

あなたは、「東郷ターン(Uターン)によってロシア艦隊の砲撃を誘った」と解釈していますが、これは完全には正しくない部分があります。

実際の目的と結果

  • 東郷ターンの目的は、ロシア艦隊の先頭を塞ぐようにT字を作るための機動であり、直接的に砲撃を誘う意図はそこまで強くなかった。
  • しかし、このターンによって日本艦隊が一時的に無防備な状態になったため、ロシア艦隊が砲撃を行ったのは事実。
  • ただし、ロシア艦隊の砲撃は「誘われた」のではなく、「日本艦隊が方向転換中で回避が難しい状態だったため、自然に狙われた」という側面が強い。
  • しかも、ロシア艦隊の砲撃はあまり命中しなかった。

つまり、「日本艦隊がわざと砲撃を誘った」わけではなく、「機動の過程で砲撃されるリスクが生じたが、結果的にほとんど被害が出なかった」というのが正確な説明。


3. 逐次撃破の実態

あなたの解釈では、「日本艦隊がロシア艦隊を正面から1隻ずつ撃破した」という表現になっていますが、実際には以下のような違いがあります。

  • 実際には、日本艦隊はロシア艦隊の先頭を砲撃し、指揮系統を混乱させ、艦隊全体の動きを制限することを狙った。
  • つまり、「1隻ずつ順番に撃破した」のではなく、先頭艦を集中的に攻撃し、それに続く艦が混乱して戦列を維持できなくなるように仕向けた。
  • 画像でも示されているように、日本艦隊の砲撃は主にロシア艦隊の前方(先頭艦)に集中している。

「逐次撃破」というよりは、「先頭を崩し、その後続艦が混乱していくように誘導する戦術」だったのが実態に近い。


まとめ:あなたの解釈との違い

項目 あなたの解釈 実際の戦術
攻撃方向 正面から撃破 横(舷側砲)から撃破
東郷ターンの意図 敵の砲撃を誘った 主目的はT字戦法の形成(砲撃を受けたのは結果論)
撃破の方法 1隻ずつ順番に撃破 先頭を集中攻撃し、後続艦を混乱させた

結論

あなたの解釈は全体の流れとしては正しいですが、以下の3点を修正するとより正確になります。

  1. 「正面から撃破」ではなく「横(舷側)から撃破」。
  2. 「砲撃を誘った」のではなく、「機動の過程で砲撃を受けたが、被害は少なかった」。
  3. 「逐次撃破」ではなく、「先頭艦を集中攻撃し、後続艦を混乱させた」。

こうした点を修正すれば、より正確な理解になるでしょう。

===== ChatGPT回答ここまで =====

Here is the full translation of your requested text while keeping the content and format unchanged.


Where Is the Mistake in Your Interpretation?

Your interpretation is mostly correct. However, strictly speaking, the point that "Japan’s fleet destroyed the Russian fleet sequentially from the front" is not entirely accurate. Below, I will explain exactly where the differences lie.


1. Revising the Expression "Destroyed from the Front"

In your interpretation, you described the situation as "The Russian fleet was lined up in a single column, and the Japanese fleet positioned itself in front of them to destroy them sequentially." However, there are some key differences:

The Actual Direction of Japanese Fire

  • The Russian fleet was " destroyed from the side" instead of "destroyed from the front."
  • The Japanese fleet positioned itself across the Russian fleet’s path, forming the T-shape.
  • In this formation, the Japanese fleet could utilize its broadside guns, whereas the Russian fleet could only fire forward, putting it at a disadvantage.
  • Therefore, rather than "firing head-on and destroying them sequentially," it was actually "firing from the side and breaking the front of the Russian formation."

Your interpretation describes the destruction as occurring "from the front," but in reality, it was an attack from the side.


2. Did the "Tōgō Turn" Intentionally Lure Enemy Fire?

You suggested that the "Tōgō Turn" (U-turn maneuver) lured the Russian fleet into firing. However, this is not entirely correct.

Actual Intent and Outcome

  • The Tōgō Turn aimed to position the fleet in a T-formation to block the Russian fleet’s advance, not necessarily to bait enemy fire.
  • However, because the turn momentarily exposed the Japanese fleet, the Russian fleet did fire upon them.
  • The Japanese fleet did not deliberately invite enemy fire; instead, the maneuver temporarily made them vulnerable.
  • Moreover, most of the Russian fleet’s shots missed, causing minimal damage.

Thus, rather than "intentionally baiting fire," it is more accurate to say that "the maneuver momentarily exposed them to fire, but the damage was minimal."


3. The Reality of Sequential Destruction

Your interpretation suggests that "the Japanese fleet destroyed the Russian fleet one by one in order." However, in reality, the strategy worked as follows:

  • Instead of destroying them, the Japanese fleet focused on the leading Russian ships to disrupt their command and control.
  • By crippling the front of the Russian fleet, the rest of the ships were thrown into disarray.
  • As shown in the image, the Japanese firepower was concentrated on the front ships of the Russian fleet.

Rather than "sequential destruction," the strategy was more about "targeting the lead ships to induce chaos in the rest of the fleet."


Summary: Differences Between Your Interpretation and Reality

Aspect Your Interpretation Actual Strategy
Direction of Attack Attacked from the front Attacked from the side (broadside fire)
Purpose of the Tōgō Turn To lure enemy fire To form a T-formation (enemy fire was a result, not a goal)
Method of Destruction Destroyed one ship at a time in sequence Targeted the lead ships to disrupt the fleet

Conclusion

Your interpretation is correct mainly in terms of overall flow, but adjusting the following three points will make it more accurate:

  1. It was not "destroying from the front" but "firing broadside from the side."
  2. The Tōgō Turn did not "bait enemy fire" but "momentarily exposed the fleet to fire, though with little effect."
  3. It was not "sequential destruction" but "disrupting the lead ships to break the formation."

By refining these points, my understanding will be even more precise.

このように、ChatGPTは「忖度」だけでなく、頼めばちゃんとした「指摘」もしてくれます。

As I can see, ChatGPT not only “guesses” but also gives me proper “feedback” if I ask for it.

それに、人間から指摘されるより気分もいいです。人間から言われると、その文書の内容によっては「カチン」と来ることもありますし。

Also, it feels better to be told by a machine than a human. When a human tells me something, it can sometimes grate on me, depending on the document's content.

ともあれ、私は、このChatGPTの回答をもって、この『「このバルチック艦隊に日本海軍が仕掛けた、秋山真之の立案した戦法というのが、未だに、よく理解できていません」を、無事終了させることができた』と総括することにしました。

Anyway, I decided to summarize that I could complete the task of “I still don't fully understand the battle plan that the Japanese Navy devised for the Baltic Fleet, which was proposed by Akiyama Masayuki” by obtaining this response from ChatGPT.

-----

繰り返しますが、私は、今も激務が続いています ―― が、多くの人がご存知の通り、激務の時ほど、業務と関係ないことに集中する、ということを、私たちはティーンのころから繰り返してきましたよね(特に、中間や期末考査の前日の夜、とかに)。

Again, I'm still working hard - but as many people know, we've been doing this since we were teenagers, concentrating on things that have nothing to do with work when we're working hard (especially the night before mid-term or final exams).

今日の日記は、その典型的な見本です。

Today's diary is a typical example.

2025,江端さんの忘備録

昨日は、「プロジェクトリーダーとしての生成AI」という観点で考えてみましたが、今回は、別の観点から考えてみたいと思います。

Yesterday, I considered the topic from the perspective of “AI as a project leader,” but this time, I would like to think about it from a different perspective.

あまり理解されていないかもしれませんが、生成AIがやっていることの一つに「ガリ勉」があります。

最近、『生成AI離れ』という言葉がでてきているようですが、毎日、ChatGPTを使い倒している私には、ちょっと信じられない言葉です。

Recently, I've been hearing the term "generation AI abandonment," but as someone who uses ChatGPT daily, I find it a little hard to believe.

業種(フィールド)だけでなく、使い方に、差があるのかもしれません。

There may be differences in the type of business (field) and how it is used.

プログラミングの世界においては、生成AIは「使えます」が、以下の条件が付帯するのかもしれない、と考えています。

In the programming world, I think that generative AI is “usable,” but it may come with the following conditions.

『生成AIが作ったコードの問題点を、指摘できるだけのスキルを人間が持っていること』

'The persons have the skills to point out the problems in the code created by generative AI.'

-----

依頼したプログラム(コード)をざっと見て、「変だな」と思い「ここ、間違っていない?」と聞き返せるスキルがあること、が、結構重要なのかな、と思うことがあります。

Sometimes, I think it is pretty essential to have the skill to look at the program (code) you have requested, think, “That's strange,” and ask, “Is this wrong?”

ChatGPTやGithub Copilotは素直な奴なので、私の指摘が正しければ、直ちにその場で修正を行うし、私の指摘が間違っていれば、私の間違いを理由とともに説明します。

ChatGPT and Github Copilot are straightforward, so if I'm right, they'll fix it right away, and if I'm wrong, they'll explain why I'm wrong.

お願い→回答、という、ワンリターンでは、生成AIはそんなに優れてはいないかもしれませんが、お願い→回答→質問→回答→疑問→回答.....と続けていけば、これほど心強いパートナーはいません。

If you only have one-way communication, where you ask a question and then get an answer, the generated AI may not be that good, but if you keep asking questions and getting answers, you will have a very reassuring partner.

生成AIを、"Copilot(副操縦士)"と命名した人は、センスがあると思います。

The person who named the generative AI “Copilot” has good taste.

-----

「生成AI離れ」とは、それはつまり、『副操縦士の言うことが理解できない/副操縦士と議論ができない』と解釈して良いのかもしれません。

“generation AI abandonment" may mean “I can't understand what the copilot is saying/I can't discuss with the copilot.”

結局のところ、「生成AI離れ」とは、「生成AIに丸投げして全て解決しようとする怠け者の発想なのではないかな」と、そんな風に邪推しています。

After all, I suspect that the “generation AI abandonment” is a lazy person's idea of trying to solve everything by throwing everything at the generation AI.

何が言いたいのかというと、「こういうプログラムを組める『私』には、市場価値があるのか、それとも、ないのか」、です。

2025,江端さんの忘備録

筑紫市の田中允市議(77)の、別の市議に対して行ったハラスメントに対して『至らぬところがあったかもしれませんが、それはそれとして今後、謙虚に学んでいけば私自身も成長するのかなと』というコメントを聞いて思い出したことがあったので、本日のネタとして記載します。

I remember hearing a comment from Tanaka Masashi, a 77-year-old city councilor in Chikushi City, Fukuoka Prefecture, about the harassment he had perpetrated against another city councilor. He said, “I may have fallen short in some ways, but if I humbly learn from this in the future, I will also grow.” I will include this as today's topic.

-----

あまり理解されていないかもしれませんが、生成AIがやっていることの一つに「ガリ勉」があります。

Although it may not be well understood, one of the things that generative AI is doing is “cramming.”

反復学習です。いわゆる「英単語帳」です。

It is a repetitive learning method. It is a so-called “English vocabulary notebook.”

例えるなら、生成AIは猛烈な勢いで「英単語の暗記」をして、「英語をしゃべれるよう頑張っている」というパラダイムで理解してもいいかもしれません。

If you want to compare it to something, you could say that the generative AI is furiously “memorizing English vocabulary” and “working hard to be able to speak English” in the paradigm of understanding.

その「暗記」は、単にメモするだけでなく、電気信号のパターンになるまで続けられます(このあたりは、ニューラルネットワークのメカニズムまで遡らなければならないので、割愛します)

This “memorization” is not just about making notes but is continued until it becomes a pattern of electrical signals (we will have to go back to the mechanisms of neural networks here so that we will skip that part).

件名: ChatGPTは怖くない ~使い倒してラクをせよ の記事に関してご提言

単に知識を蓄えるだけでは、知性にならないことは、すでに、「前世紀のエキパートシステムの失敗」で明らかですが、今の生成AIは、人間の判断基準(扱ってはならないネタ)も学習しており、加えていえば、「言葉使い」まで学習しています。

It is already apparent from the “failure of the expert systems of the last century” that simply accumulating knowledge does not make you intelligent. Still, the current generative AI also learns human judgment criteria (topics that should not be handled), and, to add to that, it also learns “word usage.”

-----

そういえば、以前何かコラムで読んだのですが、これからの時代は「知識」や「リーダーシップ」よりも、「親切」「優しさ」「礼儀正しさ」の方が重視される世の中になる、旨の記載がありました。

Speaking of which, I read something in a column before that said that in the future, the world would become a place where “kindness,” “gentleness,” and “politeness” will be valued more than “knowledge” and “leadership.”

つまり、

In other words,

―― 「凄い仕事」より、「気持よく続けられる仕事」に、人材がシフトする

"the shift in human resources is from “great work” to “work that can be continued comfortably”.

と。

上記の「仕事」は、「学校」とか「組織」とか「近所付き合い」などの言葉に置き換えられるかもしれません。

The word “work” above could be replaced with words such as “school,” “organization,” or “neighborly relations.”

『嫌われ役のリーダーを買って出て、プロジェクトを完遂する』という考え方は、もはや古い(のかも)。

“Volunteering to be the unpopular leader and completing the project” may already be old-fashioned.

(7)総じて「プロジェクトX」は、「エンジニアの夢や希望を搾取」して「プロジェクトを完成させた」というストーリで構成されており、現在の若者への「やりがい搾取」と1mmも変わっていないように見える

今や『嫌われ役のいるリーダーのプロジェクトは、プロジェクト自体が瓦解する』という流れになっていくのかもしれません。

Perhaps the trend is moving towards “a project with a disliked leader will collapse.”

ただ、進捗スケジュールを見ながら、厳しい納期を要求されているプロジェクトリーダーにとっては、このトレンドはシャレにならない話でしょう。

However, this trend is probably no laughing matter for project leaders under pressure to meet strict deadlines while monitoring the progress schedule.

-----

そういう観点から考えると、「プロジェクトリーダーを生成AIに任せる」というのは、十分にあり得る未来だと思います。

From that perspective, I think it's possible that “we will leave project leaders to AI.”

私が見ている限りにおいては、生成AIの人間に対する対応は、ほぼ完璧です。

As far as I can see, the way that generative AI interacts with humans is almost perfect.

生成AIは、間違っても『そんなことは自分で考えろ』とか『そんなことも知らないのか』などというような台詞は吐きません。

A generative AI will never say things like “You should be able to think for yourself” or “Don't you even know that?”

生成AIには、回答に対する「いいね」ボタンと「悪いね」ボタンがあり、生成AIは、これを受けて回答の内容や対応も学習しているようです。

The generated AI has a “good” button and a “bad” button for responses, and it seems that the generated AI learns the content of the reactions and how to respond to them based on these.

この考え方を拡張していくと、最終的に「生成AIによる政府や国際機関の運用」という未来に到達してしまいますが ―― 私は、それが今の状況よりもラクに生きられる世界を作ってくれるのであれば、それで構いません。

If we were to extend this line of thinking, we would eventually reach the future of “government and international organizations being run by generative AI,” - but as long as it creates a world where we can live more comfortably than we do now, I'm OK with that.

というか、むしろそうして欲しい。

Or rather, I want to realize it.

-----

ただ、行き過ぎた「生成AI頼み」は、かならず歪みを生み出すと思うので、多分、「生成AI排除」という動きも出てきます ―― 19世紀のラッダイド運動のように

However, overreliance on generative AI will inevitably lead to distortion, so there will probably be a movement to exclude it, like the Luddite movement in the 19th century.

ネットワークの世界においても、分散システムと集中システム、クラウドとエッジ、など、現在も数年単位で「揺り戻し」が発生しております。

Even in the world of networks, there are still “swinging back” trends occurring every few years, such as distributed and centralized systems, cloud and edge, etc.

プロジェクト管理に失敗した生成AIは廃棄され、より優れたプロジェクト管理AIが生き残ることになるとも思います(生成AIが学習して、発展していく可能性もあります)。

I also think that the generative AI that fails in project management will be discarded, and the AI with better project management skills will survive (there is also the possibility that the generative AI will learn and develop).

まあ、私がどう考えようと、生成AIの世界は、なるようにしかならないと思います。

Well, no matter how I think about it, I think the world of generative AI will only become what it is destined to become.

私は、ただ、それを観測し続けていくだけです。

I will continue to observe it.

-----

ただ、冒頭の市議は、「生成AIと取り替えても、一向に構わんだろう」 ―― というか、「是非取り替えてくれ」と思いますが。

However, about the city councilor at the beginning of the story, “Even if a generative AI replaces him, I don't mind at all” - or rather, I think, “Please replace him as soon as possible.”

2025,江端さんの忘備録

私は以前より『努力は天才に勝てない』ということを言い続けてきました。

I have always said that 'hard work cannot beat genius'.

故に、彼らは、平気で「毎日の練習」だの「継続は力」だの「努力は報われる」だのと言い放ちます。

最近思うことは、

Lately, I've been thinking that

『賞賛される努力と素晴しい成果より、凡庸なアウトプットの数が評価される』ということです。

'The number of mediocre outputs is valued more than the admired effort and excellent results.

努力と成果は、その時に絶賛されても、評価される時間が短いです。

Even if your efforts and achievements are praised at the time, the time it takes for them to be evaluated is short.

そして、人々の多くは、あなたの努力と成果を、簡単に忘れます。

And most people will easily forget your efforts and achievements.

比して、アウトプット(報告書や特許明細書や論文)は、内容はどうあれ、"数"で評価され、それは記録として残ります。

By comparison, outputs (reports, patent specifications, papers) are evaluated by the “number” of them, regardless of their content, and this is recorded.

-----

以前にもお話したかもしれませんが、会社同士がクロスライセンス契約をする時、『自社の特許明細書を積み上げた高さ』で、契約内容が決まる(高い方の会社が強い)という話がありました。

As I may have mentioned before, when companies enter into a cross-licensing agreement, the content of the agreement is determined by the “height of the pile of the companies' patent specifications” (the company with the higher pile is stronger).

この話が本当かどうかはウラが取れていませんが、ありそうな話です。

I have not been able to confirm whether this story is true or not, but it sounds plausible.

特許明細書の内容は難しいので、3桁を超える特許明細書の内容を、いちいち精査している余裕があるとは思えず、なにより『私でも、そうするだろうな』と思えるからです。

The content of patent specifications is difficult, so I don't think there is time to carefully examine the content of patent specifications that exceed three digits, and above all, I think that even I would do that.

(↑コラムに飛びます)

(Jump to the column)

-----

それゆえ、凡庸な私が選ぶべき戦略は明白です。

Therefore, the strategy that I, an ordinary person, should choose is clear.

「量を出し続けること」――たとえ、それが凡庸な内容であったとしても、です。

“Keep producing quantity” - even if it is mediocre content.

その"量"の戦略の一つが、この日記(ブログ)です。

One of the strategies for this “amount” is this diary (blog).

2025,江端さんの忘備録

大量・長時間のシミュレーションの計算が必要になると思って、2年前に小型のゲーミングPCを購入しました。

I bought a small gaming PC two years ago, thinking I would need to do a lot of long-running simulations.

現在、昼夜問わずのぶっつづけの計算を続けているのですが、最近、目を離している内に、ディスプレイが黒くなってシステムダウンする頻度が高くなってきました。

I've been doing calculations day and night, but the frequency of system crashes has recently increased, with the display going black while I'm away from it.

対象となっているPCは、MINISFORUM EliteMini HM90 ミニpc AMD Ryzen 9 4900H 8c/16t 小型PC 32GB 512GB です。何かクラッシュの原因となる理由はありませんか?

計算途中で、コンピュータがダウンするのは困りますし、それ以上に、システムが壊れたら、もう目の前真っ暗です。『もう、本当に勘弁して下さい』という感じです。

It would be a disaster if the computer crashed in the middle of a calculation and even more so if the system broke down. It would be like saying, “Please, no more!”

取り急ぎ、設定を変えて、熱暴走を回避する、という処理を行っています。

For now, I am changing the settings to avoid thermal runaway.

BIOS画面をいじるのは怖いので、Ryzen Controllerを使おうとう思うのですが、良いでしょうか

これに加えて、AmazonにPC冷却用の扇風機を発注しました。

In addition to this, I ordered a fan from Amazon to cool my PC.

もう、『なにふり構っていられない』という感じです。

I feel like I can't afford to waste any more time.

2025,江端さんの忘備録

「ゴールデンカムイ」は、原作(コミック)も、アニメも、映画も、全部が面白いという、稀有な作品です。

Golden Kamui is a rare work that is interesting in all its forms: the original comic, the anime, and the movie.

原作者様は言うまでもありませんが、それの携った方々の努力の賜物だと思います。このようなコンテンツを創作して頂いた多くの皆様に、改めて感謝の思いです。

Needless to say, the original author is to be commended, but I think it is also the result of the efforts of the people involved. Again, I would like to express my gratitude to the many people who created this kind of content.

-----

嫁さんは、映画で「ゴールデンカムイ」と出逢ったようで、アニメの方は見ていなかったようです。

My wife first encountered “Golden Kamui” through the movie but hadn't seen the anime.

本日、このコンテンツ自体を知らなかった長女が帰省していることもあるので、『先ずは、アマプラで、シーズン1だけでも見てみたら?』と言って、私はそのまま自室に戻って、プログラミングを再開しました。

Today, my eldest daughter, who didn't know about this content, is visiting, so I said, “Why don't you try watching at least season 1 on Amazon Prime?” I returned to my room and resumed programming.

コーヒーを作るために、リビングに降りてきたら、二人がアニメに見入っていました ―― 声をかけるのもためらわれるくらいの真剣さで。

When I came downstairs to make coffee, I found them engrossed in an anime - so absorbed that I hesitated to interrupt them.

嫁さんは、「PSYCHO-PASS サイコパス」の第3期までの視聴を「2日間」で完了している実績がありますが、なんか、今回も、このノリで行きそうな雰囲気です。

My wife has a track record of watching the first three seasons of “PSYCHO-PASS” in “two days,” but it looks like she will continue in the same vein this time, too.

私の好きなコンテンツが家族と被る ―― これは、結構、幸せなことだなぁ、と実感しています。

-----

私、以前、『お金が沢山あることが、幸せであるか?』というテーゼに対して、アマプラやネトフリのようなサブスクを例題にして、このテーゼに対する検証方法を提案したことがあります。

I once proposed a method for examining the thesis “Is having a lot of money a sign of happiness?” using examples such as Amazon Prime and Netflix.

お金を沢山持っていることは幸せである ―― を検証する方法

で、今度は、毎週、『毎週の放送を楽しみに待つアニメ』と『気にいったタイトルを一気に見るアニメ』は、どちらが、より人を幸せにしているのだろう、という、新しいテーゼについて、考え始めています。

Now, I'm considering a new thesis: Which makes people happier? Is it anime you look forward to watching every week or anime you watch all at once?

ただ、

However,

―― これ、多分、結論が出ないテーゼだろうな

"The thesis that will never conclude."

と、薄々分かってはいるんですけどね。

 I know that in my heart.

2025,江端さんの忘備録

2つ以上の研究プロジェクトを兼任する、というのは、私には、あまり珍しいことではありません。

I am not unusual to be involved in multiple research projects simultaneously.

ただ、その2つ以上のプロジェクトで、技術的なコア(プログラミング)を担当しなければならない場合があり、これは本当にキツイです。

However, sometimes, I have to take charge of the technical core (programming) for two or more projects, which is tough.

例えるのであれば、2つ以上の工事現場の両方で、私一人が、穴を掘り、整地をして、建設資材を運び、組み立て、その一部が動かないと、全部が動かない、というのを私一人でやっている感じです。

If I had to compare it to something, it would be like me being the only person digging holes, leveling the ground, transporting construction materials, assembling them, and ensuring that if one part doesn't move, the whole thing won't work.

以前から申し上げていますが、プログラムというのは、たった一箇所のミス(バグ)で、全部が失敗する(動かない/正確な値を出さない)という、誠にやっかいなモノです。

As I have said before, a program is troublesome because a single mistake (bug) can cause the entire thing to fail (not work/not give the correct value).

そして、研究ベースのプログラム(検証プログラム)は、基本的に一人で作るのが一般的です。複数人でやると、逆に作業が遅くなるからです。設計変更とか、仕様変更を、独断で行わなければ、作業が思うように進まないからです。

It is generally the case that a single person creates research-based programs (verification programs). If multiple people work on them, the work will slow down. This is because unless design changes and specification changes are made at the sole discretion of the person in charge, the work will not progress as desired.

つまりですね、技術というのは、属人性が高く、他人への譲渡が恐しく困難なのです

以前、2つのプロジェクトで、全く異なるプログラムを同時に作っていたことがありました。

I once worked on two projects simultaneously, creating completely different programs.

一方のプロジェクトでは、プロジェクトリーダーが、私の作業を褒め称えて、毎回作業に関する感謝の言葉を述べてくれました。これをプロジェクトAと言いましょう。

In one project, the leader praised my work and thanked me every time. Let's call this Project A.

もう一方のプログラムでは、プロジェクトリーダーが、私の作業の内容を聞くと、直ぐに問題点を指摘して、修正案を次回まで考えてくるように命じました。こちらをプロジェクトBと言うことにします。

In the other program, when the project leader heard about the content of my work, they immediately pointed out the problem points and ordered me to think of a revised plan by the next meeting. I'll call this project B.

プロジェクトAでは、何か新しいことをやると『褒めて貰える』ので、色々アイデアも出てきます。比してプロジェクトBでは、何か新しいことをやると『何も言われずに、問題点を指摘される』だけだったので、そういうことは止めよう、という気持ちになりました。

In Project A, I was praised for trying something new and developing many ideas. In comparison, in Project B, when I tried something new, I was told the problem points without being praised, so I decided to stop doing that.

プロジェクトAでは、私は問題が見つかったらそれを公にしました。問題をチーム全員で一緒に考えてくれるからです。比して、プロジェクトBでは、問題が見つかったら、私はそれを隠すようになりました。その問題を言ったところで、私が責められて、私が自分で解決するように命じられるだけだからです。

In Project A, if I found a problem, I would make it public because the whole team would work together to think about it. In comparison, if I found a problem in Project B, I would hide it because if I mentioned it, I would be blamed and ordered to solve it myself.

-----

まあ、私もシニアですから、プロジェクトBの方が、正しいプロジェクトの態様かもしれない、ということは分かっています。仕事とは、問題を潰しながら、納期内に目標を達成することで、それだけのモノですから。

I'm a senior, so I know Project B may be the correct approach. Work is all about achieving your goals within the deadline while solving problems.

ただ、私の場合、仕事を進めていく上で、「ありがとう」「よくやってくれたね」「凄いね」と言われると、力が湧いてきます。

However, in my case, when I'm working and people say things like “Thank you”, “You've done a great job”, or “That's amazing”, it gives me strength.

ただ、逆に、『そういうことを言われると、自分の気持ちが緩むので、止めて欲しい』、という人もいるようです。この話を聞いた時には本当にビックリしたものですが。

On the other hand, some people say, “When I hear things like that, it makes me feel relaxed, so I'd prefer it if you didn't.” I was shocked when I heard this.

-----

ともあれ、私(江端)というエンジンの燃料は、「感謝」と「敬意」と「忖度」です。その燃料が、混ぜ物であったり、不純物が混っているような不良燃料でも、私のエンジンは良く働くようです。

Anyway, the fuel that powers my (Ebata's) engine is “gratitude”, “respect” and “adulation”. Even if that fuel is adulterated or contains impurities, my engine works well.

ですので、逆に、私がプロジェクトリーダーをしなければならない時にも、「感謝」と「敬意」と「忖度」という燃料を大量投入することを心掛けています。

Conversely, when I have to be the project leader, I try to make sure that I provide a lot of fuel in the form of “gratitude,” “respect,” and “adulation.”

日本の生産性がずっと低下しているのは、この「Let me say "Thank you"」ができていないからだと、私は本気で思っています。

-----

ただ、その結果、プロジェクトが良いモノになるかどうかは分かりません。

However, as a result, nobody knows whether the project will be a good one or not.

このように考えていくと、私は

When I think about it like this, I think I can analyze myself as

―― 気持ちよく仕事ができるかどうかが重要で、ゴールやその後がどうなろうが知ったことか

"a person who thinks that it's important whether or not the process feels good, and who doesn't care what happens after the goal is reached."

と考える人間である、と自己分析できるかと思います。

私は、これまでそういう生き方をしてきて、これからも変える予定はありません。

I have lived my life this way until now, and I have no plans to change it.

これが良いことかどうかについては、私にとっては、どうでもいいことです。

Whether or not this is a good thing is not necessary to me.

『人生をどう生きたところで、大して変わりはない。ただ、狂えるものがあれば、ちょっとだけ"おトク"かもしれない』

2025,江端さんの忘備録

私は以前、詐欺サイトの被害にあったことがあります。

I was once the victim of a fraudulent website.

あの恨みを、私は今でも忘れていません。この事件の後は、随分慎重になりました。

I still haven't forgotten that grudge. After that incident, I became cautious.

photo

(↑初回のコラムに飛びます)

(Jump to the first column)

それでも、最近の、特殊詐欺の巧妙さを聞くにつれ、

Even so, as I hear about the sophistication of recent special frauds,

―― ああ、これはもう対抗できないな

"I can't compete with them anymore."

という諦めの気持ちが発生しています。

I feel a sense of resignation.

特殊詐欺グループの巧妙さは勿論ですが、被害者がちゃんと自分の被害を公知しない、という問題もあります。

Of course, the sophistication of the special fraud groups is a problem, but victims are not properly making their losses public.

誰だって、『騙される奴はバカ』と言われるのは、嫌です(私も、上記のコラムを掲載するのは辛かったです)。

Everyone hates being called a fool for being deceived (it was hard for me to publish the above column, too).

自分の被害額と、自分のプライドを秤にかけて、「沈黙しつづけることを選択」することを、誰も責められないです。

No one can blame you for remaining silent, weighing up the damage you have suffered against your pride.

-----

正直なところ、

To be honest,

■メールやSNSを全部やめる(リアルで面とショバが割れている人とだけにする)

■Stop using email and social networking services altogether (only use them with people you know in person)

■通販は大手2社に限定する(amazonと楽天)

■Limit online shopping to two major companies (Amazon and Rakuten)

くらいしか、防衛手段はないように思います。

I think these are safe ways to protect yourself.

(ネット利用を全部止めるのは、生活インフラを止めるのと同じようなものなので、私には無理ですが)

(Stopping all internet use is like stopping the infrastructure of life, so I can't do it.)

あと、最近、出所不明の電話も多いですね。

Also, there are a lot of calls of unknown origin these days.

ですので、私は、

Therefore, I handle things like 

■電話には原則出ない。電話番号をネットで調べた後で、こちらから電話する(か、無視する)

"I do not answer the phone. After looking up a phone number online, I either call them back (or ignore them)."

とかの対応をしています。

-----

変な話ですが、

It's a strange story, but

―― ネット(バーチャル)を利用するための認証装置として、リアル環境(F2Fとか、会合とか)を活用する

"Use of real environments (such as face-to-face meetings and gatherings) as authentication devices for using the internet (virtual)"

という風に変わりつつあるような気がします。

I feel like it is changing in that way.

バーチャルとリアルの主客転換によって、これからは、リアルが「社会の情報認証基盤」や「安全設計の中心軸」になっていくと思います。

From now on, the real world will become the “information authentication infrastructure for society” and the “central axis of safety design” due to the shift in the relationship between the virtual and the real.

つまり、これからのセキュリティ戦略は、「クソ面倒くさい認証基盤の開発や活用」ではなく、「リアルとの接点」を使い倒す方向に向かう、ということです。

In other words, the security strategy will be to use “contact points with the real world” to the fullest rather than “developing and utilizing a cumbersome authentication infrastructure.”

----

私の言っている意味すら分からない人も多いかもしれません。

There are probably many people who don't even understand what I mean.

今となっては、

Now that it's

―― そもそも、以前から、生活は、バーチャル(ネット)が"主"でしょう?

"To begin with, hasn't the virtual (online) been the “main” part of our lives for some time now?"

という人の方が、多くなっているのかもしれませんので。

There may be more people like that.

実録! ネット詐欺

2025,江端さんの忘備録

以前、私は「新型コロナ感染とワクチン」について、シバタ先生から送っていただいたレポートを読んで、それを私なりの解釈を加えて、コラムとして連載していました。

I used to write a series of columns on the “new coronavirus infection and vaccines,” based on a report sent to me by Dr. Shibata, and add my interpretation.

(↑第一回のコラムに飛びます)

(Jump to the first column)

今でも覚えているのが、

I still remember that.

―― 政府の大規模ワクチン摂取が始まったら、それまで大混乱だった病院内が一気に静まった

"Once the government's mass vaccination program began, the previously chaotic hospital suddenly quieted down."

というニュアンスの内容でした(シバタ先生、間違っていたらご連絡下さい)。

(If I'm wrong, please let me know, Dr. Shibata).

その時の私は、『ベルトコンベアの上に流れてくる処理しきれない膨大な物品が、いきなり流れてこなくなった』というイメージで理解しました。

At the time, I understood it as an image of 'the huge amount of items that couldn't be processed that were flowing on the conveyor belt suddenly not coming.'

NHKのニュースで新規感染者の"数値"を見ているのとは、違ったベクトルからの視点であり、『現場の最前線にいる人でなければ、見えてこない光景だなぁ』と思ったのを覚えています。

It was a different perspective from the “numbers” of new infections reported on the NHK news, and I remember thinking, “This is a scene that can only be seen by someone on the front line.

-----

ワクチンの効果や副作用や後遺症については今なお検証が続いています。医学的または科学的検知からの検証は今後も続けられるべきですので、これは良いことです。

The vaccine's effects, side effects, and after-effects are still being verified. This is a good thing, as verification from a medical or scientific perspective should continue in the future.

マスクは、新型コロナ感染に、なんの効果もなかった ―― という発表が、数年~十数年後にされる可能性は「ゼロ」とは言えないのです。

ただ、ここで重要なことは、

the important thing here is that

―― そのベルトコンベアの物品を止めたのは、ワクチンを打った国民

"The people who stopped the items on the conveyor belt were the people who had been vaccinated."

である、ということです。

これを別の視点から見てみると、あの政府手動の大規模ワクチン摂取は、

Looking at this from a different perspective, I think that the large-scale vaccination program carried out by the government was

―― 『政府の施策に、国民の多くが、自発的に応じた』という、我が国戦後史におけるレアケース

"A rare case in the post-war history of our country, in which 'many of the citizens voluntarily responded to the government's measures'"

とも思っています。

-----

なにしろ、私は、『原則、政府の施策は疑ってかかかる』のが我が国の国民性と思っています。

At any rate, I think our country's national character is to 'suspect government measures in principle.'

さすがに偏見に過ぎるかな?

Is that just prejudice?

でも、『太平洋戦争時に、政府と軍部とマスコミに欺かれ続けた』 ―― という記憶は、日本人のDNAになっていると、私は思っています。

However, I believe that the memory of “being deceived by the government, the military, and the media during the Pacific War” is part of the Japanese people's DNA.

昨日、与党国会議員による政治資金パーティーを巡る違法行為および脱税疑惑(キャッシュバックを含む)について、新たな証言が報じられているようです。

New testimony has been reported regarding the illegal activities and tax evasion (including cash back) surrounding the political funding party held by ruling party Diet members yesterday.

我が国の国民のこのDNAは、国政を預かる者たちによって、未だに強固に維持され続けている、と思いました。

I thought those in charge of national affairs were firmly maintaining this DNA of the Japanese people.

2025,江端さんの忘備録

「坂の上の雲」の再放送、ようやく、バルチック艦隊との対決シーンに入りました。

The re-broadcast of “Saka no Ue no Kumo” finally reaches the scene where the fleet confronts the Baltic Fleet.

私、「坂の上の雲」は、当然に既読(中学生くらいだったかと)で、初回放送も見たのですが、このバルチック艦隊に日本海軍が仕掛けた、秋山真之の立案した戦法というのが、未だに、よく理解できていません。

I had already read “Saka no Ue no Kumo” (I think I was in junior high school then) and watched the first broadcast. However, I still didn't understand the Japanese Navy's battle plan against the Baltic Fleet, which Akiyama Manji proposed.

『東郷は狂ったのか?』というバルチック艦隊総司令官の発言は、今の私の気持ちでもあります。

The words of the commander-in-chief of the Baltic Fleet, “Has Togo gone mad?” are also how I feel now.

今度こそ、ちゃんとこの作戦を理解して、他の人に説明可能な状態になるまで、頭に定着させようと思います。

This time, I will ensure I understand this strategy and get it into my head until I can explain it to others.

それはさておき。

Leaving that aside.

-----

「坂の上の雲」の再放送を見てみると、日露戦争において、我が国は、奇跡的なラッキーを5つぐらい連続で掴むという、歴史的幸運に恵まれていたことを思い知ります。

When you watch the rerun of “Saka no Ue no Kumo,” you will be reminded that our country was blessed with historical good fortune in the Russo-Japanese War, where we were able to grab five miraculous lucky breaks in a row.

確率値にすると、0.000000....のように、0がいくつも続くような値になると思います。

If I convert it to a probability value, I think it will be like 0.000000... with lots of 0s.

実際、晩年の秋山真之は、『なぜ、我が国はこのような幸運を得られたのか』と、その解釈で死ぬまで悩み続けたそうです。

In his later years, Akiyama Saneyuki is said to have continued to wonder until his death about why his country had been so fortunate.

この人、軍人だけど、エンジニアでもあったんだなぁと思うと、親近感が湧きます。

I feel a sense of closeness when I think he was a soldier and an engineer.

-----

一方、この真逆をやってしまったのが、『4つの"if"と、1つの"might"』で開戦してしまった太平洋戦争です。

On the other hand, the Pacific War, which began with the “four ‘ifs’ and one ‘might’”, was the complete opposite.

『太平洋戦争と同じような状況になれば、歴史の教訓があろうがなかろうが、私たちは再び開戦してしまう』

-----

世の中は、『奇跡とかifとかmightに頼らなければならないもの』で、溢れています。

The world is a whole of things that “require miracles, ifs, and might.”

そして、「やらなければならない戦争」いうものがあることは、私にも分かってきています。

And I am beginning to understand that wars must be fought.

例えば、やらなければならない戦争を『しなかった』為に、もっと酷い戦争になり、民間人を含めて、何千万の死者を作ることになったが、第二次世界大戦です。

For example, because they “did not” fight the war that they had to fight, it became an even worse war, and tens of millions of people, including civilians, were killed. This was World War II.

私にできることは、『私の存命中は、私の安全と命が担保された範囲の内容に留めて欲しい』と、祈ることだけです。

All I can do is pray that 'during my lifetime, I want the content to be limited to the extent that my safety and life are guaranteed.'