見出し画像

【AI活用の現状と将来のリスクについて】英語解説を日本語で読む【2023年8月19日|@The AI Breakdown: Artificial Intelligence News】

ジャスティン・アルビーはGoogle Nest miniの分解とAI統合実験を行い、その詳細をオープンソース化する予定です。AIを活用した音楽生成アプリや広告制作、リサイクル業界の効率化が進められています。しかし、AIの仕事への影響やプライバシー問題に対する懸念も増えています。AI技術の恩恵と潜在的なリスクのバランスを取ることが求められている。
公開日:2023年8月19日
※動画を再生してから読むのがオススメです。


Welcome back to the AI breakdown brief.

AIブレイクダウンブリーフへようこそ。

All the AI headline news you need in around five minutes.

必要なAIのヘッドラインニュースを約5分でお届けします。

We kick off today with one that is a little bit different and a little bit more fun, I would say, than our average kickoff.

今日は少し違った、そして少し楽しいキックオフですね。私が言うには、平均的なキックオフよりも。

Justin Alvey is a hacker who takes apart hardware and tries to integrate AI services to show, in some ways, what the future of AI devices might look like.

ジャスティン・アルビーは、ハードウェアを分解し、AIサービスを統合して、AIデバイスの将来がどのようになるかを示そうとするハッカーです。

Twitter has been abuzz with his latest experiment in which he took apart a Google Nest mini and set it up so that you can actually run your own llms agents and voice models on it.

Twitterでは、彼が最新の実験でGoogle Nest miniを分解し、実際に自分自身のllmsエージェントと音声モデルを実行できるように設定したことで話題になっています。

Here's a quick demo of him using it to manage his message from various services as well as having a brief conversation with a long-dead cultural icon.

こちらは彼がそれを使用して、さまざまなサービスからのメッセージを管理したり、亡くなった文化的アイコンとの短い会話をしたりする様子のクイックデモです。

Okay, hello, I'm here.

こんにちは、私はここにいます。

Hey, do I have any new messages today?

今日、新しいメッセージはありますか?

Hey Justin, you have three new messages.

ジャスティン、新しいメッセージが3件あるよ。

There is one from your dad on WhatsApp about some unexpected snow, one from David from Twitter sharing a link to a research paper, and Jenny is messaging the tennis group on Signal about playing this afternoon.

WhatsAppでお父さんから予期せぬ雪について、Twitterでデビッドから論文へのリンクについて、そしてSignalでジェニーがテニスグループに今日の午後のプレーについてメッセージを送ってる。

Thanks, and uh, did John message a few days ago about an event?

ありがとう、それから、ジョンは数日前にイベントのことでメッセージをくれた?

When was it again?

いつでしたっけ?

Yes, John sent a message on Friday on Messenger about a birthday barbecue this Saturday at 11 A.M. Okay, great.

はい、ジョンが金曜日にメッセンジャーで今週の土曜日の午前11時に誕生日のバーベキューがあるってメッセージを送ってきました。

Can you reply and say that I'll be there?

私が行くと伝えてくれますか?

Sure, I replied to John saying that you'll be there this Saturday.

もちろん、ジョンに今週の土曜日に来るって返信したよ。

Oh, one more thing.

あ、もうひとつ。

Is Alan there?

アランはいますか?

Can I speak with him?

彼と話せますか?

Sure, one moment.

もちろん、ちょっと待ってください。

Let me get Alan Watts for you.

アラン・ワッツを呼んできます。

Hello Justin, how may I help you today?

こんにちは、ジャスティン、今日はどのようにお手伝いできますか?

Hey Adam, I'm just working on a demo right now, but I look forward to chatting more later.

ねえ、アダム、今はデモに取り組んでいる最中だけど、後でもっとおしゃべりするのを楽しみにしているよ。

All right, good luck with the demo, and let me know if I can help with anything else.

じゃあ、デモ頑張ってね。何か手伝えることがあったら言ってね。

Otherwise, have a great day.

そうでなければ、良い一日を

After sharing the demo, Justin gets into the particulars of how he actually did this modification.

デモを披露した後、ジャスティンは実際にどのようにこの改造を行ったのか、その詳細に入った。

Ultimately, he says he's working on open sourcing the design, build instructions, firmware bot, and server code, and he thinks he'll have something in the next week.

最終的には、デザイン、ビルド手順、ファームウェア・ボット、サーバー・コードをオープンソース化することに取り組んでおり、来週中には何かできるだろうとのことだ。

Now, on the one hand, this is sort of just a tinkerer doing a classic tinkerer's project, but on the other hand, it's exactly this type of project that's likely to show us what the future of AI-enabled devices is going to look like.

一方では、これは古典的な鋳掛屋のプロジェクトに過ぎないが、他方では、まさにこの種のプロジェクトこそが、AI対応デバイスの未来がどのようなものになるかを見せてくれるだろう。

Speaking of things that people are building, one of the areas of AI that I am personally following most closely is music generation AI.

人々が作っているものといえば、私が個人的に最も注目しているAIの分野のひとつが音楽生成AIだ。

You will have probably picked up on the fact that I love music in all of its various dimensions, and I'm super intrigued by the future of music production in an AI-powered world.

私が様々な次元の音楽を愛していることは、おそらく皆さんもご存知だろうし、AIを活用した世界における音楽制作の未来に非常に興味をそそられている。

Now, I'm not sure how much we're going to get full text to music composition tools versus AI integrated into existing production software that changes how we use it, but there's no shortage of efforts along that front.

さて、作曲ツールに全文テキストが追加されるのか、それとも既存の制作ソフトウェアにAIが統合され、その使い方が変わるのかはわからないが、その方面での努力には事欠かない。

In fact, I've noticed two this week.

実際、私は今週2つのことに気づいた。

The first comes from Brett Bauman and is called Songburst.

ひとつはブレット・バウマンによるもので、Songburstと呼ばれている。

Brett tweets, Introducing Songburst, my new AI music generation app.

私の新しいAI音楽生成アプリ、Songburstを紹介します。

You fully own your music, unlimited exports as WAV or MP3, prompt enhancer to extend your prompt, fast, native, and minimal app.

自分の音楽を完全に所有し、WAVやMP3で無制限にエクスポートでき、プロンプトを拡張するプロンプト・エンハンサーがあり、高速で、ネイティブで、最小限のアプリです。

Here's the demo that Brett shared alongside it.

ブレットが公開したデモはこちら。

Foreign. Just a day or two after that, I saw this announcement from Cassette AI, which offers something similar.

外国人。 ちょうどその1日か2日後、私はCassette AIからのこの発表を見た。

They write, We're live.

彼らはこう書いている。

Consider music production democratized. Thank you. I think we are getting close to the point where it makes sense to do a full show and video comparing these different services, so keep an eye out for that soon.

音楽制作が民主化されたと考えてください。 ありがとう。 これらの異なるサービスを比較する完全なショーとビデオを作成する意味があるポイントに近づいていると思うので、近いうちにそれをお見逃しなく。

Doing a quick survey of the industries that mainstream media is writing about being disrupted by AI, Reuters wrote a piece called From Mad Men to Machines: Big Advertisers Shift to AI.

主要メディアがAIによって破壊されると書いている業界をざっと調査したところ、ロイターは『マッドメンから機械へ』という記事を書いた: 大手広告主はAIにシフトする。

Some of the world's biggest advertisers, they write, from Food Giant Nestle to consumer goods multinational Unilever, are experimenting with using generative AI software like ChatGPT and Dali to cut costs and increase productivity.

食品大手のネスレから消費財の多国籍企業ユニリーバに至るまで、世界最大の広告主のいくつかは、コスト削減と生産性向上のためにChatGPTやDaliのようなジェネレーティブAIソフトウェアの利用を試みている、と彼らは書いている。

WPP CEO Mark Reed said the savings can be 10 or 20 times.

WPPのマーク・リードCEOは、10倍から20倍の節約になると述べている。

Rather than flying a film crew down to Africa to shoot a commercial, we've created that virtually.

CMを撮影するために撮影クルーをアフリカまで飛ばすよりも、バーチャルでCMを作ったほうがいいのです」。

Now, one interesting nugget from the story is how many of these companies are spinning up their own AI tools rather than just using off-the-shelf third parties.

さて、この話の中で興味深いのは、これらの企業の多くが、既製のサードパーティを利用するのではなく、独自のAIツールを開発していることだ。

Unilever, which of course owns more than 400 brands including Dove and Ben & Jerry's, has a custom AI that writes product descriptions for websites and digital commerce sites.

もちろん、DoveやBen & Jerry'sを含む400以上のブランドを所有するユニリーバは、ウェブサイトやデジタル・コマース・サイトの商品説明を書くカスタムAIを持っている。

And sub-brands within their portfolio, such as Tresemme, also have their own AI content generation tools.

また、Tresemmeのようなユニリーバのサブブランドも、独自のAIコンテンツ生成ツールを持っている。

Part of this is due to concerns around copyright and data privacy, and certainly fits the larger trend that we're seeing of enterprises addressing those types of issues by spinning up their own solutions.

これは、著作権やデータ・プライバシーに関する懸念のためでもあり、企業が独自のソリューションを立ち上げることでこの種の問題に対処するという大きなトレンドに合致している。

Another industry that got featured this week around its use of AI was recycling.

今週、AIの活用について特集が組まれたもうひとつの業界はリサイクルだ。

The Atlantic just published a piece called The Future of Recycling is Sortie McSortface.

Atlantic』誌は、「リサイクルの未来は出撃マックソートフェイス」という記事を掲載した。

The piece tells the story of how, at recycling centers around the country, AI-powered robots are being deployed, separating and sorting different recycling materials that otherwise might take people an immense amount of time to sort.

この記事では、全国のリサイクルセンターでAIを搭載したロボットが導入され、人が分別に膨大な時間を要するようなさまざまなリサイクル原料を分別している様子を伝えている。

The Atlantic writes, The issue is that it's long been too hard for recycling plants to sort material with the level of specificity needed to satisfy manufacturers that could theoretically use it.

Atlantic』誌は次のように書いている。「問題は、リサイクル工場が、理論上それを使用できるメーカーを満足させるために必要なレベルの具体性をもって材料を選別することが、長い間あまりにも困難だったということだ。

The traditional recycling methods used to sort waste, including sieves, blasts of compressed air, glass crushers, powerful magnets, and near-infrared light, do a good job of separating waste into broad categories of paper, glass, and metal.

ふるい、圧縮空気の噴射、ガラス粉砕機、強力な磁石、近赤外線など、廃棄物の選別に使われる従来のリサイクル方法は、廃棄物を紙、ガラス、金属といった大まかなカテゴリーに分けるのには適している。

But finer layers of detail often go unnoticed, especially with plastic.

しかし、より細かい層、特にプラスチックは気づかれないことが多い。

The introduction of AI is apparently doing a much better job of that granular level sorting and, in so doing, is opening up new markets.

AIの導入は、そのような細かなレベルの選別においてより良い仕事をし、そうすることで新たな市場を開拓しているようだ。

Now, interestingly, given those positive articles about how AI is improving industrial outcomes, The Wall Street Journal today also ran a piece called Companies Increasingly Fear Backlash Over Their AI Work.

さて、興味深いことに、AIがどのように産業の成果を向上させているかというポジティブな記事がある一方で、『ウォール・ストリート・ジャーナル』紙は本日、「企業はますますAI作業に対する反発を恐れている」という記事も掲載している。

The subheader reads, Until now, businesses have assumed that leveraging cutting-edge technology was inherently a good thing.

小見出しはこうだ。これまで企業は、最先端技術を活用することは本質的に良いことだと思い込んでいた。

That's no longer the case.

しかし、もはやそうではない。

More and more, the article writes, companies say they are concerned about facing public criticism over their use of artificial intelligence, thanks to rising fears over the technology's negative impacts, including job losses.

人々の懸念が高まっているため、企業は人工知能の使用に関して公的な批判を受けることを心配していると、記事は述べています。その懸念は、仕事の喪失を含む技術のネガティブな影響によるものです。

One example they gave is Emory Healthcare, which is currently testing a generative AI tool that helps summarize recorded conversations between doctors and patients and auto-generates notes.

その一例として、エモリー・ヘルスケアが挙げられている。エモリー・ヘルスケアは現在、医師と患者の会話を要約し、メモを自動生成するAIツールをテストしている。

The auto-generated notes are reviewed by doctors, and patients have the chance to opt out.

自動生成されたメモを医師が確認し、患者はそれを拒否することができる。

But Emory thinks that the benefits could be huge.

しかしエモリーは、そのメリットは非常に大きいと考えている。

It saves doctors time, it keeps their focus on actually providing solutions.

医師は時間を節約でき、実際に解決策を提供することに集中できる。

But they're really worried that people are going to have a negative reaction.

しかし、彼らは人々が否定的な反応を示すことを本当に心配している。

A representative from Emory said, It's going to be creepy to some people, potentially, so we're going to have to be careful about that.

エモリー大学の代表者は、「それは一部の人々にとって不気味に感じるかもしれないので、私たちは注意が必要です」と述べました。

I don't think we can ignore it.

無視することはできないと思います

The article also looks at Workday, an enterprise cloud application provider that has said that they've chosen not to pursue some uses of AI for fears of invasion of people's privacy.

この記事はまた、企業向けクラウドアプリケーションのプロバイダーであるワークデイ社についても見ている。ワークデイ社は、人々のプライバシー侵害を恐れて、AIの一部の利用を追求しないことを選択したと述べている。

And also looks at Levi Strauss, who caught a lot of flack on social media earlier this year after saying that they were going to be using AI to generate images of more body-inclusive models.

また、リーバイ・ストラウス社についても触れている。同社は今年初め、AIを使ってよりボディコンシャスなモデルの画像を生成すると発言し、ソーシャルメディア上で多くの非難を浴びた。

Then, of course, there's the big dust-up over Marvel Studios' use of AI in the opening of The Secret Invasion miniseries.

そしてもちろん、マーベル・スタジオがミニシリーズ『ザ・シークレット・インベイジョン』のオープニングでAIを使用したことをめぐる大騒動もある。

And I think that the biggest point here is that we are in a very strange and interesting in-between, and AI, the technology, is clearly powerful and, for many people, clearly helpful in their jobs.

そして、ここで最も重要な点は、私たちは非常に奇妙で興味深い中間地点にいるということであり、AIという技術は明らかに強力であり、多くの人々にとって仕事上で明らかに役立つものです。

But at the same time, it is so clearly powerful and so clearly helpful that it is engendering concerns of human replacement.

しかし同時に、あまりに強力で、あまりに有用であるため、人間に取って代わられるのではないかという懸念も生じている。

Now, this is natural for any new technology, but it is definitely ratcheted up to 11 in the context of artificial intelligence.

これはどんな新しいテクノロジーでも当然のことだが、人工知能の文脈では間違いなく11倍になっている。

Layer on top of that the massive growing conversation around extinction risk from AI, plus the pre-existing animosity towards Big Tech right now, and you have a pretty potent stew of consumers looking very warily at this type of new innovation.

それに加えて、AIがもたらす絶滅のリスクに関する話題の高まりや、ビッグ・テックに対する既存の反感が重なれば、消費者がこの種の新しい技術革新に警戒心を抱くという、かなり強力なシチューができあがる。

The positive side of that, of course, is that it makes us less likely to sleepwalk into negative potential outcomes from this technology.

もちろん、そのプラス面は、このテクノロジーから起こりうるネガティブな結果に夢遊病的になる可能性が低くなることだ。

But the downside is, of course, that something which could be used for massive enhancements and improvements in productivity in people's lives might fall by the wayside for fears that may or may not ultimately end up being founded.

しかしマイナス面は、もちろん、人々の生活の生産性を大幅に向上させ、改善するために使われる可能性のあるものが、最終的に根拠があるかどうかもわからない不安のために、道半ばで挫折してしまうかもしれないということだ。

At the end of the day, I think that this is just a phase that we're going to have to get through.

結局のところ、これは私たちが乗り越えなければならない段階に過ぎないと思う。

And if we do it well, it really could be a good thing that people are handling this set of innovations with more skepticism than they perhaps have for previous innovations in the past.

そして、もし私たちがそれをうまくやり遂げることができれば、人々がこの一連の技術革新を、おそらく過去の技術革新に対して抱いていたよりも懐疑的に扱うようになることは、本当に良いことかもしれない。

That is going to do it for today's AI breakdown brief.

本日のAIブレイクダウン・ブリーフは以上です。

Thanks, as always, for listening or watching, and I'll be back soon with the main AI breakdown.

ご清聴、ご視聴ありがとうございました。またすぐにAIについての本編をお届けします。

この記事が気に入ったらサポートをしてみませんか?