そのうち、『自分の書いた拙い文章を、そのまま流して、炎上起す奴ってバカなの?』と言われる時代が、来るかもしれません。

SNSによる中傷事件が後を断ちませんが、SNSに限らず、メール、書き込み、落書き、そしてブログも、文字によるメッセージは、全て人の心を破壊する機能があります。

The number of slander cases on social networking sites, emails, posts, graffiti, and blogs is endless; written messages can destroy people's hearts.

そもそも「文字メッセージ」は、(1)現実世界のコミュニケーションを伴わないし、(2)応答に数時間以上のタイムラグが発生するし、(3)背景状況を共有できない、という厄介な性質があります。

To begin with, “text messages” have the troublesome properties of (1) not involving communication in the real world, (2) causing a time lag of several hours or more in response, and (3) not being able to share the background situation.

そう考えると、そもそも「文字メッセージ」というのは、不完全で出来損ないのコミュニケーションツールといっても良いでしょう。

When we think about it like that, we could say that “text messages” are an imperfect and flawed communication tool.

で、この「不完全で出来損ないのツール」を、輪をかけて不完全で文章作成リテラシーのない人間が取り扱えば、「最悪」と呼ばれるものになるのは当然です。

So, it is only natural that if this “imperfect and inadequate tool” is handled by someone who is even more imperfect and lacks writing literacy, it will become "something worse."

いっそのこと、SNSとかメールとかブログとかを記載する権限を、免許制度にしても良いのではないでしょうか ―― SNSが、交通事故と同様に、人を傷付け、殺害するものなのは明かなのですから。

Why not make it a licensing system that requires people to have permission to use social networking services, email, blogs, etc. - because it is clear that social networking services can hurt and even kill people in the same way as traffic accidents.

ずっと無事故でSNSを運用できたら、"ゴールドSNSer"として特典を得られ、逆に、中傷メッセージの申立があったら罰則が課せられ、免停やSNSプラットフォームから永久追放しても良いかもしれません。

Suppose you can operate your SNS account without any accidents. In that case, they will reward you as a “Gold SNSer,” but they may punish you and even be banned from the SNS platform if you receive a complaint about a defamatory message.

しかし、そういう制度は、簡単に権力サイドが濫用する(言論統制)ので、法制度に入れない方がいいですが ―― 「民間機関による格付け」くらいのサービスなら、だれかやってもいいとは思います。

However, such a system could easily be abused by those in power (to control speech), so it would be better not to include it in the legal system. However, if it is a service like “rating by a private organization,” anyone can do it.

しかし、一方、民間でそういうサービスを始めれば、ネット上の組織的なイジメできるようになります ―― とまあ、どれほど考えても、『これ』といった決め手がありません。

However, if such a service starts in the private sector, it will become possible to cyber-bully systematically on the internet. Therefore, no matter how much you think about it, there is no 'decisive factor.'

―― 「SNSでの誹謗中傷はやめよう」とは言う人はいても、「SNSを使うのをやめよう」と言う人はいない

-----

そこで提案なのですが、『生成AIを使った文案作成』というのはどうでしょうか。

So, I have a suggestion: how about 'drafting using generative AI'?

今、ChatGPTと、以下のようなやりとりをしてみました。

I tried the following conversation with ChatGPT.

===== ChatGPTへの依頼ここから =====

===== Request to ChatGPT From here =====

以下のメールの文章を、パワハラと感じさせないような文章に変換して下さい。

Please convert the following email text to avoid sounding like power harassment.

『先週金曜日に提出されるべき報告書を私は受けとっていません。至急提出して下さい。』

“I have not received the report due to be submitted last Friday. Please submit it as soon as possible.”

===== ChatGPTへの依頼ここまで =====

===== Request to ChatGPT ends here =====

===== ChatGPTからの回答ここから =====

===== Answer from ChatGPT =====

以下のように修正すると、柔らかく、パワハラと感じさせない表現になります。

If you make the following changes, the expression will become softer and less likely to be perceived as power harassment.

『先週金曜日に提出予定だった報告書がまだ確認できていないのですが、状況はいかがでしょうか?お忙しいところ恐縮ですが、可能であれば早めにご対応いただけると助かります。』

'I haven't been able to check the report due last Friday, so I was wondering how things are going. I apologize for bothering you when you are busy, but it would be a big help if you could respond as soon as possible.

この表現では、相手にプレッシャーを与えず、報告書がまだ届いていないことを丁寧に伝えつつ、急ぎで対応してもらいたい旨を伝えています。

This expression politely conveys that the report has not yet arrived without putting pressure on the other party and requests that they respond as soon as possible.

===== ChatGPTからの回答ここまで =====

===== ChatGPT's response ends here =====

生成AIは、こんなふうに文章を直してくれます。

The generative AI will fix your sentences like this.

もう、この機能そのものをSNSやメーラーに標準装備しても良いと思います。

This function is standard equipment for social networking services and email clients.

私が知らないだけで、すでに実装されているような気がする、と思い調べてみたところ、"Grammarly"、"HyperWrite"、"Assistr.ai"などのツールがあるようです ―― というか、"Grammarly"は、私が有償で使っているツールです(ずっと英文翻訳のチェックに使っていましたが、たしかに"Tone"とかいう項目がありました)。

I thought that there might be tools like “Grammarly,” “HyperWrite,” and “Assistr.ai” that I just didn't know about, so I looked into them. It seems that there are tools like that—or rather, “Grammarly” is a tool that I use for a fee (I've been using it to check English translations, and there is indeed an item called “Tone”).

それはさておき。

Leaving that aside.

-----

「文字メッセージ」による、日本史上最悪の事件は、これです。

The following is the worst case in Japanese history involving “text messages.”

ですので、私は、政治家同士の外交には、同時翻訳ツールを使うことを提言しています。

Therefore, I am proposing using simultaneous translation tools for diplomacy between politicians.

『外交問題の原因をAIに押し付けることができる』ようにするためです。

we can 'force the cause of foreign policy problems onto AI.'

これと同じように、SNSによる中傷事件も、生成AI(ChatGPTなど)に押しつけるのが一番簡単です。

In the same way, defamation cases on social networking sites are the most accessible means to push onto generative AI (such as ChatGPT).

それに、生成AIの作成する文章では、こういう事件は発生しにくいでしょう。

In addition, it is unlikely that a sentence created by a generative AI would cause such an incident.

そのうち、『自分の書いた拙い文章を、そのまま流して、炎上起す奴ってバカなの?』と言われる時代が、来るかもしれません。

Before long, there may come a time when people say, “Are you stupid for letting your poor writing go out as it is and causing a stir?”.

2024,江端さんの忘備録

Posted by ebata