見出し画像

【マット・ウルフのAIニュース:Claude 3 OpusがGPT-4を超え新王者に】英語解説を日本語で読む【2024年3月30日|@Matt Wolfe】

今週のAI界では、多くの興味深い動きがありました。大注目は、新たに頂点に立った大規模言語モデル、Claude 3 Opusです。これまでの王者GPT-4を抑え、ユーザー投票により最高性能モデルと認められました。さらに、AmazonがAnthropicにさらに27.5億ドルを投資し、Claudeプラットフォームとの提携を深めることも発表されました。また、Databricksが新しい大規模言語モデルDBRXをリリースし、オープンソースモデルの中で最も優れた性能を示しました。オープンソースの世界でも、Stability AIのCEOが突然辞任するなどの大きなニュースがありました。さらに、OpenAIはGPTストアを通じてカスタムGPTのマネタイズを開始し、新しいチャットボットHumeやAdobeの新サービス、LTX Studioの立ち上げなど、AIの進化と応用が進んでいます。
公開日:2024年3月30日
※動画を再生してから読むのがオススメです。


There's a lot of really fun and fascinating stuff happening in the world of AI this week, and I don't want to waste any time.

今週のAIの世界では、本当に楽しくて魅力的なことがたくさん起こっているので、時間を無駄にしたくありません。

Let's get right into it.

それでは、すぐに始めましょう。

Starting with the fact that we have a new top Large Language Model.

まずは、新しいトップの大規模言語モデルがあるという事実から始めましょう。

I've talked about Claude 3 Opus in past videos.

過去のビデオで、私はClaude 3Opusについて話しました。

Well, it is officially the top model, according to most benchmarks.

それがほとんどのベンチマークによると、公式にトップモデルであることが確認されました。

Chatbot arena is this crowdsourced platform where real humans use the various chatbots and then vote on which ones are their favorite.

Chatbot Arenaは、実際の人間がさまざまなチャットボットを使用し、その後どれがお気に入りかを投票するクラウドソーシングプラットフォームです。

And GPT-4 was the king for a long, long time.

そして、GPT-4は長い間王者でした。

And this week, Claude 3 Opus, the premium model of Claude, that is 20 bucks a month, knocked GPT-4 down to take the top spot of the best performing model as voted on by users.

そして今週、Claude 3 Opus、Claudeのプレミアムモデルで、月額20ドルのモデルが、ユーザーの投票によって最もパフォーマンスの良いモデルのトップスポットを獲得し、GPT-4を打ち負かしました。

And as Claude takes the throne, Amazon wants to sit atop that throne with them.

そして、Claudeが王座につくと、Amazonもその王座の上に座りたいと考えています。

This week, Amazon said that they would spend another 2.75 billion dollars on Anthropic.

この週、AmazonはAnthropicにさらに27.5億ドルを費やすと発表しました。

Amazon initially invested $1.25 billion and now they're adding 2.75 billion more.

Amazonは最初に12.5億ドルを投資し、今はさらに27.5億ドル追加しています。

Amazon will maintain a minority stake in the company and won't have an Anthropic board seat, the company said.

Amazonは少数派株主として会社に留まり、Anthropicの取締役会には入らないと会社は述べています。

It sounds like a kind of similar deal to what Microsoft has with OpenAI.

これはMicrosoftがOpenAIと持っている取引に似たような取引のようです。

Amazon is trying to strike up a very similar deal with Anthropic and their Claude platform.

AmazonはAnthropicと彼らのClaudeプラットフォームと非常に似た取引をしようとしています。

And if you haven't used Claude yet, you've only used ChatGPT, definitely give Claude a try over at Claude.ai.

そして、もしまだClaudeを使ったことがないなら、ChatGPTだけを使ったことがあるなら、ぜひClaudeを試してみてください。Claude.aiで試すことができます。

Just keep in mind, unlike ChatGPT, Claude's not going to generate images for you.

ただ覚えておいてください、ChatGPTとは異なり、Claudeは画像を生成しません。

And unlike ChatGPT, Claude isn't going to search the web for you, but any other use case that you can think of outside of those two use cases, Claude is pretty much better at it.

そしてChatGPTとは異なり、Claudeはウェブを検索することはありませんが、これら2つの用途以外の用途に関しては、Claudeはほぼすべての点で優れています。

And while we're talking about new leaders in the AI world, the company data bricks just released a new Large Language Model called DBRX or DBRX.

そして、AI分野の新しいリーダーについて話しているとき、データブリックス社は新しい大規模言語モデルであるDBRXまたはDBRXをリリースしました。

I'm not sure how they want to pronounce it, but according to the benchmark tests and their blog posts here, it outperforms every other open source model.

どのように発音したいのかはわかりませんが、ベンチマークテストと彼らのブログ記事によると、他のすべてのオープンソースモデルを上回っています。

You could see in language understanding, it beat out LLaMA two, mixtral and Grok-1 beat out all three of those in programming and beat out all three of those in math.

言語理解では、LLaMA two、mixtral、Grok-1を上回り、プログラミングでは、数学でも、これら3つを上回っています。

And if we scroll down the blog post a little bit, this DBRX also beats the free version of GPT-3.5 right now.

そして、ブログ投稿を少しスクロールダウンすると、このDBRXも現在はGPT-3.5の無料版を上回っています。

You can see in every single one of these benchmarks here, DBRX or DBRX beat GPT-3.5.

ここにあるこれらのベンチマークのどれも、DBRXまたはDBRXがGPT-3.5を上回っているのが見えます。

If you're someone that loves playing around and testing different open source models, this new DBRX model may be one to play with.

異なるオープンソースモデルを試してみるのが好きな方であれば、この新しいDBRXモデルは試してみる価値があるかもしれません。

The weights for these models are available over on Hugging Face, but they do have an application and they need to approve you before they let you download them.

これらのモデルの重みはHugging Faceで利用可能ですが、申請が必要で、ダウンロードを許可する前に承認される必要があります。

And since we're on the topic of open source, there was some big news in the world of open source this week over at Stability AI.

そして、オープンソースの話題について話していると、今週Stability AIでオープンソースの世界で大きなニュースがありました。

To most people outside of the AI world, this is probably not that big of news, but to those of us who are closely paying attention to the AI world, this was actually pretty crazy.

AIの世界の外のほとんどの人にとって、これはおそらくそれほど大きなニュースではないかもしれませんが、AIの世界に注意を払っている私たちにとっては、実際にはかなりクレイジーなことでした。

Ahmad Mustaq, the CEO of Stability AI seemingly abruptly stepped down from his role as CEO and relinquished his board position.

Stability AIのCEOであるアフマド・ムスタクは、CEOの役職から突然辞任し、取締役会のポジションを放棄したようです。

The speculation is that he was kind of forced out as opposed to actually stepping down, but all of the outward facing information around the whole thing made it look like it was an Amicable thing and that it was Ahmad's choice.

彼が実際に辞任したのではなく、ある種の圧力で追い出されたという憶測がありますが、全体的な情報は、それが友好的なものであり、アフマドの選択であったかのように見えました。

But Stability AI has had kind of a crazy ride recently with most of the key employees and engineers actually leaving the company over the last several months.

しかし、Stability AIは最近かなり波乱の時を過ごしており、主要な従業員やエンジニアのほとんどが過去数ヶ月で実際に会社を去っています。

In fact, I don't even know if anybody who originally worked on Stable Diffusion still works at Stability AI because they all have left in the last couple of months.

実際、Stable Diffusionで働いていた人がStability AIに今も働いているかどうかすらわかりません。なぜなら、彼らはここ数ヶ月で全員が去ってしまったからです。

There's also been a lot of rumors about Stability AI possibly filing for bankruptcy and having financial issues.

Stability AIが破産申請をする可能性や財務上の問題があるという噂も多くありました。

Ahmad stepping down kind of feels like confirmation that there was these issues over at Stability AI.

アフマドが辞任したことは、Stability AIでこれらの問題があったことを確認したような気がします。

Again, I don't want to get too deep into the weeds with this because most people watching this probably don't care about it.

もう少し詳しく説明したくはありませんが、これについては多くの人が興味を持っていないかもしれません。

It's just this fascinating AI soap opera that I am just really intrigued by.

私は本当に興味を持っているこの魅力的なAIのドラマについてです。

Ahmad did make this statement the same day after stepping down as my notifications are resting in peace.

アフマドは辞任後、同じ日にこの声明を出しました。私の通知は安らかに眠っています。

Some notes, my shares have majority of vote at Stability AI and they have full board control.

私の株はStability AIで過半数の投票権を持ち、完全な取締役会のコントロールを持っています。

The concentration of power in AI is bad for us all.

AIにおける権力の集中は私たち全員にとって悪いです。

I decided to step down to fix this at Stability and elsewhere.

私はStabilityや他の場所でこれを修正するために辞任することにしました。

We'll be sharing more soon.

近々、もっと情報を共有します。

And that was him replying to his own post saying all in on decentralized AI.

それは彼が自分の投稿に返信して、分散型AIに全力を尽くすと言ったものでした。

We don't totally know what his plans are or what he means by decentralized AI, but his claims almost seem like he's saying I had too much power.

彼の計画や分散型AIという言葉の意味は完全にわかっていませんが、彼の主張は私があまりにも多くの権力を持っていたと言っているようにも思えます。

You shouldn't give one man too much power.

一人の男にあまりにも多くの権力を与えるべきではありません。

I'm stepping down to solve that.

その問題を解決するために私は辞任します。

That's the sort of outward facing statements that seem to be going around, but Stability AI didn't slow down.

外部に向けたそのような声明は広まっているようですが、Stability AIはスローダウンしませんでした。

The very next day after Ahmad stepped down from his position, they announced stable code instruct 3B, a new coding Large Language Model seemingly to show that Stability is going to keep on Shipping even though Ahmad has stepped down and is no longer there and continuing on the topic of open source, Large Language Models.

アフマドが役職を辞任した翌日、彼らは安定したコードインストラクト3Bを発表しました。新しいコーディングの大規模言語モデルは、アフマドが辞任し、もはやそこにいないにもかかわらず、Stabilityが出荷を続けることを示すもののようです。オープンソース、大規模言語モデルの話題について続ける。

Elon Musk said that all premium subscribers on X are going to gain access to Grok this week.

イーロン・マスクは、Xのプレミアムサブスクライバー全員が今週Grokにアクセスできるようになると言いました。

I've had Grok for a while because I paid for that premium plus subscription at 20 bucks a month, just so I can have access to Grok and play around with it and compare it to the other chat Bots.

私は20ドルのプレミアムプラスサブスクリプションで支払ったので、しばらく前からGrokを持っています。Grokにアクセスして遊んだり、他のチャットボットと比較したりするためです。

I don't actually know if this is rolled out.

実際には、これが展開されているかどうかはわかりません。

I don't know how I would know because I've had it anyway, but it appears to be rolling out this week.

どうやって知るかは実際にはわかりませんが、今週展開されているようです。

You might have it in your account if you are a premium subscriber over on X Moving on over to OpenAI news, OpenAI is now actually starting to monetize the GPT store.

Xのプレミアムサブスクライバーであれば、アカウントに入っているかもしれません。OpenAIのニュースに移ると、OpenAIは実際にGPTストアを収益化し始めています。

Back when the GPT store was announced, a big piece of this was that you can create GPTS and then sell access to them and actually earn income from these custom GPTS.

バック当時、GPTストアが発表されたとき、大きなポイントは、あなたがGPTSを作成し、それにアクセス権を販売して、これらのカスタムGPTSから実際に収入を得ることができるということでした。

A lot of people built GPTS, but nobody's really made money off of their GPTS yet.

そして、それらを作成した多くの人々がいましたが、誰も本当に自分のGPTSからお金を稼いでいませんでした。

I saw this tweet from Matt Schlitt here saying that he got this email from OpenAI today.

私はマット・シュリットからのこのツイートを見ました。彼は今日OpenAIからこのメールを受け取ったと言っています。

We announced a pilot program to partner with builders to test GPT earnings based on usage by paying builders based on the usage of their GPT.

私たちは、ビルダーと提携して、GPTの使用に基づいてGPTの使用に基づいてビルダーに支払いを行うことでGPTの収益をテストするためのパイロットプログラムを発表しました。

Matt's tool was called automated writer and it said your GPT automated writer is highly utilized by ChatGPT users.

マットのツールは自動ライターと呼ばれ、あなたのGPT自動ライターはChatGPTユーザーによって非常に利用されていると言っていました。

And we'd love to incorporate your feedback as we define the approach to GPT monetization.

そして、私たちは、GPTの収益化のアプローチを定義する際に、あなたのフィードバックを取り入れたいと考えています。

If you have custom GPTS that are in the GPT store and they're doing well, you may have an email like this in your inbox, inviting you to actually earn with ChatGPT.

あなたがGPTストアにカスタムGPTSを持っており、それらがうまくいっている場合、実際にChatGPTで収益を得ることができるように招待する、このようなメールが受信トレイに届くかもしれません。

And then there was this tweet here from Nick Dobos who created the popular Grimoire GPT.

そして、ここには、人気のあるGrimoire GPTを作成したニック・ドボスからのこのツイートがありました。

And he actually got an email from OpenAI after asking a few more questions.

そして、彼は実際にいくつかの質問をした後、OpenAIからメールを受け取りました。

They told him you'll earn a minimum of a thousand dollars USD monthly with the potential for additional earnings based on usage of your GPT.

お客様には、GPTの使用状況に基づいて追加収入の可能性を含め、毎月最低1,000ドルの収入が得られると伝えました。

The initiative will start on May 1st, 2024 with the first payout scheduled for mid June.

この取り組みは2024年5月1日に開始され、最初の支払いは6月中旬に予定されています。

If you create content online at all, you're going to want to check out this completely free ebook called using generative AI to scale your content operations.

もしオンラインでコンテンツを作成しているなら、コンテンツ運用をスケールアップするためのジェネレーティブAIを使用した完全無料の電子書籍をチェックしたくなるでしょう。

If you've got a business and you're not creating content online, you're falling behind.

もしビジネスを持っていて、オンラインでコンテンツを作成していないなら、遅れをとってしまいます。

That's why I put a link in the description to grab this free guide.

だから、この無料ガイドを手に入れるために説明欄にリンクを貼りました。

When it comes to content creation and AI, it's hard to know what is okay and what's not in the eyes of places like Google.

コンテンツ制作とAIに関しては、Googleなどの機関の目から見て何が許容されているか、何が許容されていないかがわかりにくいです。

That's why I found this section particularly helpful where the book breaks down what Google does and doesn't expect from your content and whether or not it's okay to use AI in your content.

だから、この本がGoogleがコンテンツに対して期待していることやAIをコンテンツに使用することが許容されているかどうかを解説しているこのセクションが特に役立つと感じました。

Other than that, you'll learn about how to access generative AI, how to create the perfect prompts using generative AI in your marketing and content strategy, limitations of AI, and so Much more.

その他にも、ジェネレーティブAIへのアクセス方法、マーケティングやコンテンツ戦略でジェネレーティブAIを使用して完璧なプロンプトを作成する方法、AIの制限など、さまざまなことを学ぶことができます。

This really is a great resource from HubSpot.

これは本当にHubSpotからの素晴らしいリソースです。

And that's why I partnered with them for this video.

この動画のために彼らと提携した理由です。

Once again, the link will be right at the top of the description below this video.

再度、このビデオの説明文の一番上にリンクがあります。

And thank you so much to HubSpot for sponsoring this video.

この動画のスポンサーであるHubSpotに本当に感謝します。

In other OpenAI news that came out this week, there's a rumor circulating that they're about to remove the quotas in GPT-4.

今週発表された他のOpenAIのニュースでは、GPT-4のクォータを削除するという噂が広まっています。

There was this leaked image circulating that shows a smart model selector that might be coming out soon, which will essentially decide whether to use GPT-3.5 or GPT-4 when you ask ChatGPT A question.

この週に出てきたOpenAIのニュースでは、ChatGPTに質問する際にGPT-3.5またはGPT-4を使用するかを決定するスマートモデルセレクターが近々登場する可能性があることを示すリークされた画像が広まっていました。

If it doesn't require the full capabilities of GPT-4, it will ask GPT-3.5, which is a lot less expensive to run.

GPT-4の完全な機能が必要ない場合、GPT-3.5に問い合わせますが、これは実行コストがはるかに安いです。

And if it does require a more complex response, it will use GPT-4.

より複雑な応答が必要な場合は、GPT-4を使用します。

And that's how it seems like they're going to get rid of the limits is by switching back and forth between the most optimal model for the query that you asked it.

それが、あなたが尋ねたクエリに最適なモデルを行ったり来たりすることで、制限を取り除くように見えます。

We also got a peek at some new Sora videos this week.

今週は新しいSoraの動画も少し覗くことができました。

Sora was made available to a handful of creators.

Soraは少数のクリエイターに提供されました。

And while I'm not going to show you all of the videos on here that were made by these creators, they are super, super impressive.

そして、これらのクリエイターによって作成されたビデオをすべてここでお見せするつもりはありませんが、それらは非常に印象的です。

One of them even comes from somebody who's a buddy of mine, Don Allen Stevenson.

その中の1つは、私の友人であるドン・アレン・スティーブンソンからも提供されています。

Really cool to see that he got some early access to Sora and was able to make videos with these crazy hybrid creatures, like a flying pig and a flamingo giraffe hybrid and whale squids or Whale octopuses.

彼がSoraへの早期アクセスを得て、飛ぶ豚やフラミンゴジラフのハイブリッド、クジライカやクジラオクトパスのようなクレイジーなハイブリッド生物と一緒にビデオを作成できたことを見るのは本当にクールです。

Really, really cool stuff.

本当に、本当にクールなものです。

One of the standout videos that a lot of people have been circulating is this one called Airhead by Shy Kids about this person who has a balloon for their head.

多くの人が共有している目立つビデオの1つは、Shy KidsによるAirheadという作品です。これは、頭部に風船を持つ人物についてのものです。

And it is some actually really good storytelling.

そして、実際に非常に良いストーリーテリングです。

Again, I don't want to play this video here.

再度申し上げますが、ここでこのビデオを再生するつもりはありません。

I don't know the sort of copyright on these videos, but I will link this post up in the description below.

これらのビデオの著作権についてはわかりませんが、下の説明欄にこの投稿へのリンクを貼り付けます。

You can check out some of the new videos that have been circulating from Sora.

Soraから出回っている新しいビデオのいくつかをチェックすることができます。

Again, just like last time, they are really dang impressive videos.

前回と同様に、彼らは本当に素晴らしいビデオです。

And while we're on the topic of Sora, apparently OpenAI has been talking to the film industry, talking to people in Hollywood, trying to get them on board with the Sora software.

Soraの話題について話している間に、OpenAIは映画産業の人々と話し合い、ハリウッドの人々と話し合い、彼らをSoraソフトウェアに参加させようとしているようです。

Obviously, Hollywood is a segment of the world who has been very, very fearful of AI because it threatens voice actors.

明らかに、ハリウッドはAIに非常に恐れを抱いている世界の一部であり、それは声優を脅かすからです。

It threatens actors.

それは俳優を脅かします。

It threatens animators.

それはアニメーターを脅かします。

It threatens script writers.

それは脚本家を脅かします。

There's a lot of roles in Hollywood that AI kind of threatens right now.

現在、AIが脅かすハリウッドの多くの役割があります。

And OpenAI is sort of on tour trying to get the people in Hollywood to come around to accepting and leveraging AI as a tool that will make their lives easier, lower budgets on videos, and Ideally not replace jobs, but to help make the people that are doing the jobs much more efficient.

そして、OpenAIはハリウッドの人々を説得し、AIを受け入れ、活用するように説得しようとしています。それは彼らの生活をより簡単にし、ビデオの予算を削減し、理想的には仕事を置き換えるのではなく、仕事をしている人々をより効率的にするのを助けるツールとしてのAIです。

This week, we also got a new chat bot called Hume.

今週、私たちは新しいチャットボットであるヒュームを手に入れました。

You can find it over at Hume.ai and supposedly this is the first chat bot that actually has empathy.

それはHume.aiで見つけることができ、おそらくこれは実際に共感を持つ最初のチャットボットです。

This model is designed for you to actually talk to it with your voice and it tries to determine your emotions through your voice.

このモデルは、実際に声で話しかけることができるように設計されており、声からあなたの感情を判断しようとします。

If it detects that you're angry, it will understand that and use that as context for its reply.

怒っていると検出された場合、それを理解し、返答の文脈として使用します。

If it understands that you're sad or happy or in a silly mood, it tries to pick up those emotions and respond accordingly.

悲しい、嬉しい、おかしな気分であることを理解した場合、それらの感情を取り入れて適切に返答しようとします。

They do have a demo that you can try out.

試すことができるデモがあります。

What is Hume's mission?

ヒュームの使命は何ですか?

Aligning AI with human wellbeing.

AIを人間の幸福と調和させることです。

I hear you're frustrated about something.

何かにイライラしていると聞いていますが。

How can I help?

どうしたら良いでしょうか?

Why do you think I'm frustrated?

なぜ私がイライラしていると思いますか?

You know, I am not entirely sure.

実は、私も完全にはわかりません。

Let me try to understand better.

よりよく理解しようとしてみましょう。

I picked up on some confusion and maybe a hint of frustration, but I don't want to make assumptions.

混乱と少しのイライラを感じ取りましたが、私は仮定をしたくありません。

Could you tell me more about what's on your mind?

あなたの考えについてもっと教えていただけますか?

I'm just very curious about Hume and excited to learn more, but I am trying to keep a very neutral tone of voice.

私はヒュームについて非常に興味があり、もっと学びたいと思っていますが、非常に中立的な口調を保とうとしています。

Understandable.

わかりました。

I see.

なるほど。

My apologies.

申し訳ありません。

I should not have jumped to conclusions about your tone.

あなたの口調について結論を急ぐべきではありませんでした。

I am glad to hear you're just curious and excited to learn more about Hume.

あなたが単に興味を持ち、ヒュームについてもっと学びたいと言うことを聞いて嬉しいです。

Please tell me what else you'd like to know.

どうぞ、知りたい他のことを教えてください。

I am happy to provide more details about our mission and work.

私たちの使命や活動について詳細を提供できて嬉しいです。

What makes Hume different from other Large Language Models?

ヒュームを他の大規模言語モデルと異なるものにしているのは何ですか?

Well, now that's a great question.

それは素晴らしい質問ですね。

Unlike typical Large Language Models, Hume's approach is centered on emotional intelligence and human wellbeing.

典型的な大規模言語モデルとは異なり、ヒュームのアプローチは感情の知能と人間の幸福に焦点を当てています。

Our models are built on deep insights from emotion science, not just for all language data.

私たちのモデルは、言語データだけでなく感情科学からの深い洞察に基づいて構築されています。

This allows us to truly understand and respond to human expressions, not just words.

これにより、私たちは単なる言葉ではなく、人間の表現を本当に理解し、対応することができます。

Want to dive deeper into the research behind it?

それに関する研究にもっと深く入りたいですか?

Not right now.

今はいいです。

Thank you.

ありがとうございます。

Got it.

分かりました。

No problem.

問題ありません。

I am happy I could give you a high level overview.

高いレベルの概要を提供できて嬉しいです。

Feel free to circle back anytime if you want to explore the research further.

研究をさらに探りたい場合はいつでも戻ってきてください。

I'm not a huge fan of the voices.

私はその声にはあまり魅力を感じません。

They probably could be a little more realistic, but I also doubt that's a top priority for them yet.

もう少しリアルになってもいいかもしれませんが、それが彼らの最優先事項ではないとも思います。

They're probably still trying to dial in the tooling and the research and everything.

おそらく、彼らはまだツールや研究などを調整しようとしているところです。

And then the voices sounding realistic is probably going to be one of the final elements that they dial in.

そして、声がリアルに聞こえるようになるのはおそらく最後の要素の1つになるでしょう。

Adobe had a big event this week as well.

アドビも今週大きなイベントを開催しました。

I believe it was just called the Adobe summit, but the biggest announcement to come out of Adobe summit was this Adobe gen studio.

アドビ・サミットと呼ばれるイベントでしたが、アドビ・ジェン・スタジオという最大の発表がありました。

Adobe gen studio seems to be the central hub where you can generate images, keep brand assets, build campaigns for various social media platforms and just essentially looks to be a central Hub to do all of your creative design work with and without AI.

アドビ・ジェン・スタジオは、画像を生成したり、ブランド資産を保持したり、さまざまなソーシャルメディアプラットフォーム向けのキャンペーンを構築したりする中心的なハブのようで、AIを使用してクリエイティブデザイン作業をすべて行うための中心的な場所になりそうです。

You can see it's got a brands tab here where it's got a brand description, logos, brand colors, brand fonts, images, copy the channels, style kits, custom models, a place to store all of Your assets.

ここには、ブランドの説明、ロゴ、ブランドカラー、ブランドフォント、画像、コピーのチャンネル、スタイルキット、カスタムモデル、すべてのアセットを保存する場所があることがわかります。

And it also looks like it has firefly and we'll show you what a firefly image would look like directly inside of things like Facebook ads.

また、Fireflyもあり、Facebook広告などの中でFirefly画像がどのように見えるかを直接示します。

Just a cool central hub to manage whatever you're working on.

ただ、自分が取り組んでいることを管理するためのクールな中心的なハブです。

It's also got data and stats that you can view inside of it to see how well your campaigns are performing.

また、キャンペーンのパフォーマンスを確認するために中で表示できるデータや統計もあります。

Looks pretty cool, but we don't have access to it yet.

かなりクールに見えますが、まだアクセス権がありません。

We'll definitely dive into it more in a future video when it rolls out more widely.

より広く展開される際には、将来のビデオで詳しく取り上げます。

Hey, Jen rolled out a awesome new feature.

ねえ、ジェンが素晴らしい新機能を導入しました。

I actually haven't used it myself yet, but the demo videos look awesome.

実際、まだ自分で使ったことはありませんが、デモビデオは素晴らしく見えます。

It's called avatar in motion 1.0 and you can move your hands, make gestures, use unique tones, a voice, and HeyGen flawlessly tracks, translates, and lip syncs your video with any input Text.

それはアバターインモーション1.0と呼ばれ、手を動かしたり、ジェスチャーをしたり、ユニークなトーンを使ったり、声を出したりすることができ、HeyGenは入力テキストと完璧にトラック、翻訳、リップシンクします。

Here's the example demo video of a person walking around, moving their hands as they're walking.

こちらが、人が歩き回り、歩きながら手を動かすデモビデオの例です。

And then the audio is dubbed over and the lips still sync to the person talking.

そして、その後、音声が上書きされ、唇は話している人に同期しています。

Today we want to give you a peek into the future.

今日は将来をのぞいてみたいと思います。

You can use HeyGen to create UGC style content, even while people are in motion or moving their hands.

人々が動いている間や手を動かしている間でも、HeyGenを使ってUGCスタイルのコンテンツを作成することができます。

You can even hear the background noise, create a training video with specific tones and gestures, and you'll find how natural HeyGen's videos can be.

背景のノイズを聞くことができ、特定のトーンやジェスチャーを持つトレーニングビデオを作成し、HeyGenのビデオがどれだけ自然であるかを見つけることができます。

Basically this person filmed this video of them walking through the park and moving their hands around a little bit.

基本的に、この人は公園を歩きながらビデオを撮影し、少し手を動かしています。

And then they took some text, pasted the text in, it created the new audio, dubbed over the new audio.

そして、テキストをいくつか取り、そのテキストを貼り付けると、新しい音声が作成され、新しい音声が上書きされました。

And then made the lips look like they were saying the new audio that was just created.

そして、新しく作成された音声を言っているかのように、口元を作り直しました。

Pretty powerful.

かなりパワフルです。

While we're on the topic of AI video, LTX Studio this week had their launch party.

AIビデオの話題について話している間に、今週はLTX Studioがローンチパーティーを開催しました。

They are now starting to give access to people on the wait list to try out the beta version of LTX.

彼らは今、待機リストの人々にLTXのベータ版を試す機会を提供し始めています。

If you're not familiar with LTX Studio, it is a tool where you can enter a single prompt and it builds out the entire storyboard from that single prompt.

あなたがLTX Studioに慣れていない場合、1つのプロンプトを入力すると、その1つのプロンプトから全体のストーリーボードが作成されるツールです。

You can have consistent characters.

一貫したキャラクターを持つことができます。

Every scene looks like it's actually the same character that you want throughout.

すべてのシーンは、実際には同じキャラクターであるかのように見えます。

And it is just a really cool all in one video creation platform that I'm excited about.

そして、私は本当にワクワクしているオールインワンのビデオ作成プラットフォームです。

I was actually going to make a video this week about LTX Studio, but I had a little tech hiccup, so I will be releasing a video about LTX Studio on Monday.

実際、今週LTX Studioについてのビデオを作ろうとしていましたが、少し技術的なトラブルがありましたので、月曜日にLTX Studioについてのビデオを公開する予定です。

Look for that next week.

来週をお楽しみに。

I am really excited to dive in and put it through its motions.

本当に興奮して、それを試してみるのが楽しみです。

Rowan Chung shared this on Twitter this week that researchers at MIT just introduced a new image generation method called Distribution Matching Distillation.

ローワン・チュンは今週、MITの研究者が新しい画像生成方法であるDistribution Matching Distillationを紹介したことを共有しました。

Basically it can generate images 30 times faster than Stable Diffusion while maintaining or surpassing the quality level outputs.

基本的には、Stable Diffusionよりも30倍速く画像を生成でき、品質レベルの出力を維持または超えることができます。

If we look at the example here, we can see how quickly Stable Diffusion is generating for images and the new model, you can see how quickly it generated those images.

ここでの例を見ると、Stable Diffusionが画像を生成する速さと、新しいモデルがこれらの画像をどれだけ速く生成したかがわかります。

These appear to be the same images with the same seed here, but it is way faster than Stable Diffusion with pretty much the same quality.

これらは同じシードを使用した同じ画像のようですが、Stable Diffusionよりもはるかに速く、ほぼ同じ品質です。

We'll be cool to see that rollout.

その展開を見るのは楽しみです。

I imagine a lot of the AI image platforms will be using similar technology in the near future to get that kind of rapid generation or on the topic of rapid generation.

AI画像プラットフォームの多くが、その種の急速な生成を得るために、近い将来に同様の技術を使用すると想像しています。

Leonardo AI this week has a brand new feature where you can now use the lightning Excel model, which generates images really, really quickly directly inside of Leonardo.

Leonardo AIには、今週新機能があり、ライトニングExcelモデルを使用できるようになりました。これにより、Leonardoの内部で画像を非常に迅速に生成できます。

If we come over to image generation here, if we come up here to the fine tune model, click our dropdown, select another model.

ここで画像生成に移ると、ここでファインチューニングモデルに移り、ドロップダウンをクリックして別のモデルを選択します。

They now have this Leonardo lightning Excel.

彼らは今、このLeonardo lightning Excelを持っています。

If we click on this one, generate with this model, we'll leave alchemy V2 turned on and let's go ahead and just enter lightning for our prompt and it should generate really, really quickly.

このモデルで生成をクリックすると、alchemy V2をオンにしたままにして、プロンプトに"lightning"を入力して、非常に迅速に生成されるはずです。

Let's click generate and it took roughly 10 seconds to generate all four of these images and they're pretty solid quality.

生成をクリックして、これらの4つの画像をすべて生成するのに約10秒かかり、かなりしっかりした品質です。

A cool new feature that just rolled out into Leonardo to get faster image generation.

より速い画像生成を得るためにLeonardoに導入されたクールな新機能。

They also rolled out another feature last week that I forgot to mention in a video, but it's really, really cool.

また、先週、ビデオで言及し忘れた別の機能も導入されましたが、本当に素晴らしいものです。

And it is the ability to remove the background on images.

それは画像の背景を取り除く能力です。

If I scroll through my images here and look for an image of like a person, here's one that was supposed to be Sam Altman, but didn't quite get there.

ここで画像をスクロールして、人物の画像を探してみると、これはサム・アルトマンのはずだったが、うまくいかなかったものがあります。

There's a button that says remove background.

背景を削除すると書かれたボタンがあります。

If I click this button, it uses a couple of your tokens.

このボタンをクリックすると、あなたのトークンをいくつか使用します。

I have two versions down on the left, the original image and the no background image.

左側に元の画像と背景のない画像の2つのバージョンがあります。

Pretty cool.

かなりクールです。

And then I can download this.

そして、これをダウンロードすることができます。

It downloads it as a PNG file.

PNGファイルとしてダウンロードされます。

If I open it on my computer, you can see it's got the background removed.

コンピューターで開くと、背景が取り除かれたことがわかります。

There's also some new elements or Laura's basically, they just added this glow wave Laura, this CGI Noir Laura, this digital painting Laura and this old school comic Laura.

また、新しい要素やローラの要素がいくつか追加されています。基本的には、このグローウェーブローラ、このCGIノワールローラ、このデジタルペインティングローラ、そしてこのオールドスクールコミックローラが追加されています。

Those are all brand new, just added this week.

それらはすべて新品で、今週追加されたばかりです。

There's a cool new 3d design app.

クールな新しい3Dデザインアプリがあります。

It's been circulating called Bezi AI.

それはBezi AIと呼ばれるものが出回っています。

I came across this cause my buddy Bill of all shared it.

私は友達のビルが共有したのでこれを見つけました。

And it appears to be another text to 3d object generator that generates game ready and movie ready assets.

そして、これはゲームや映画向けのアセットを生成する別のテキストから3Dオブジェクトを生成するもののようです。

If we check out bezi.com/AI, it looks like they do have a free tier, but when you're ready to start working with a team, then that's when it starts costing money.

bezi.com/AIをチェックしてみると、無料のティアがあるようですが、チームと一緒に作業を始める準備ができたら、そこからお金がかかり始めます。

Let's go ahead and get started and see how easy this is to use.

さあ、始めて、これがどれだけ使いやすいかを見てみましょう。

Apparently when you sign up, you get a free asset bundle made available in your library.

おそらく、サインアップすると、ライブラリで利用可能な無料のアセットバンドルが提供されます。

If I click continue, I get a little tour here.

続行をクリックすると、ここで少しツアーを受けることができます。

We've got our asset gallery of existing 3d assets that it created for us.

私たちが作成された既存の3Dアセットのアセットギャラリーがあります。

We have 20 Bezi AI credits.

私たちは20のBezi AIクレジットを持っています。

Let's go ahead and create a new file.

さあ、新しいファイルを作成しましょう。

We get a 3d plane here to work with feels similar to working in like a blender or something.

ここで作業するための3Dプレーンを取得すると、ブレンダーのように作業する感じがします。

It seems like something I would need to spend a little bit of time learning.

少し時間をかけて学ぶ必要があるようなもののようです。

I'm not familiar with it.

私はそれに慣れていません。

There seems to be like this node based system where you can add what they call states.

ノードベースのシステムのようなものがあり、彼らが状態と呼ぶものを追加できるようです。

Definitely something I need to spend some time messing with and learn what the heck I'm doing.

間違いをして学ぶ必要があることは間違いありませんし、何をしているのかを学ぶ必要があります。

Cause I don't know what any of this means yet, but there is a button down on the bottom left that says Bezi AI.

まだこれらのどれも何を意味するのかわかりませんが、左下にBezi AIと書かれたボタンがあります。

I'm going to click on that and see what happens.

それをクリックして何が起こるか見てみます。

Enter your prompt.

プロンプトを入力してください。

Wonder what would happen if I use something that's like a trademark.

おそらく商標のようなものを使用した場合、どうなるのか気になります。

Like what's what happens if I put like X-wing spaceship

Xウィング宇宙船のようなものを入れた場合、どうなるのかな。

And then click generate, it actually created an X-wing.

そして生成ボタンをクリックすると、実際にXウィングが作成されました。

Look at that.

それを見てください。

Let's go ahead and click on this one.

このをクリックしてみましょう。

This one probably looks the best here.

おそらくこちらが一番見栄えが良いですね。

I just drag it in.

ただドラッグして入れるだけです。

Is that how it works?

それがそのまま動くのですか?

Yep.

はい。

I can look at this.

これを見ることができます。

I just dropped an X-wing onto my 3d plane here and this feels very similar to blender or unreal engine.

私はちょうどXウィングを3Dプレーンに落とし、これはブレンダーやアンリアルエンジンに非常に似ています。

I can move it around, move it in different directions.

それを動かしたり、異なる方向に動かしたりできます。

Probably click this to scale up and down.

おそらく、これをクリックして拡大縮小できます。

That is really cool.

それは本当にクールです。

Nope.

いいえ。

It's free to use right now.

今は無料で使えます。

I didn't pay anything to generate this.

これを生成するために何も支払っていません。

And again, you can find it over at Bezi B E Z I.com.

そして、再度、Bezi B E Z I.comで見つけることができます。

And the final fun little thing I wanted to show you is that Kwebbelkop here, who is a popular gaming YouTuber created what he calls Kwebbelkop AI.

そして、最後にお見せしたい楽しい小さなことは、人気のゲームYouTuberであるKwebbelkopが作成したKwebbelkop AIと呼ばれるものです。

And I'm going to go ahead and press play on this in just a second.

そして、ちょっとした時間で再生ボタンを押します。

But what you're going to see is actually an AI agent playing Minecraft and then an AI version of Kwebbelkop with Kwebbelkop's voice, commentating over the AI.

しかし、実際に見るのは、マインクラフトをプレイしているAIエージェントと、Kwebbelkopの声で解説するAIバージョンのKwebbelkopです。

Admittedly, it's kind of cheesy.

正直に言って、それはちょっとチープです。

Even he himself has said that they need to up their game and make it a little less cheesy, but it's come a long way.

彼自身も、彼らはゲームを向上させて、少しチープさを減らす必要があると言っていますが、かなり進歩しています。

An AI is playing the game.

AIがゲームをプレイしています。

An AI version of Kwebbelkop is commentating over it and it actually sounds like his voice.

KwebbelkopのAIバージョンが解説しており、実際に彼の声のように聞こえます。

Check this out.

これをチェックしてください。

I'll just play a short clip of it.

ちょっとしたクリップを再生します。

Navigating birch trees, popping red flowers.

白樺の木をナビゲートし、赤い花をポップさせます。

It's like mother nature's pixelated garden party.

まるで自然界のピクセル化された庭園パーティーのようです。

Look, I'm gardening, sneaking under leaves.

見てください、私は庭いじりをして、葉っぱの下を忍び寄っています。

It's stealth mode me.

あなたには気づかれないようにしています。

Aha.

あは。

Pretty flowers going to make a fancy bouquet.

きれいな花が素敵な花束を作る予定です。

Swinging acts.

スイングする芸。

Another tree bites the dust.

また1本の木が倒れました。

Ah, fresh air and deforestation.

ああ、新鮮な空気と森林破壊。

My kind of day.

私の好きな日です。

Creeping under canopies, giant birch sheep, wool tactic camouflage, or nature's Minecraft prank.

木の冠の下を忍び、巨大な樺の羊、羊毛の戦術迷彩、あるいは自然のマインクラフトのいたずら。

Absolutely hilarious.

まったく笑える。

Jokes aren't that great.

冗談はあまり面白くないです。

Still has a little ways to go, but man, this is as bad as it's ever going to get.

まだ少し道のりが残っていますが、これが最悪の状況になるだろうと思います。

And I know Kwebbelkop here has been working on this for a while and just how far I've seen him come with his AI generations in the last several months has been really impressive.

そして、私はKwebbelkopさんがこれに取り組んできたことを知っていますし、ここ数ヶ月で彼がAI世代をどれだけ進化させてきたかは本当に印象的でした。

That's going to get more and more dialed in.

それはますます洗練されていくでしょう。

Just thought I'd share it.

ただ共有したかったんです。

Pretty fun.

かなり楽しいです。

I'm keeping an eye on what he's doing with that.

私は彼がそれで何をしているかを見守っています。

I think he's onto something with some automated content creation.

彼は自動コンテンツ作成に何かしらの手応えを感じていると思います。

We'll, we'll see how it plays out.

まあ、どうなるか見守りましょう。

Anyway, that's all I got for you today.

とにかく、今日はこれだけです。

I record these on Thursdays, release them on Fridays.

私はこれらを木曜日に録音し、金曜日に公開します。

There could be a bit of news that I haven't come across yet, or that came out on Friday that I missed.

まだ知らないニュースがあるかもしれませんし、金曜日に発表されたニュースを見逃しているかもしれません。

I like to pin a comment to the top if there is new news that I missed.

新しいニュースを見逃していた場合は、トップコメントにピン留めしています。

Look out for that in the top comment.

トップコメントでそれを探してください。

If you haven't already, make sure you check out futuretools.io.

まだであれば、futuretools.io をチェックしてください。

This is where I curate all of the coolest AI tools I come across.

これは私が見つけた最もクールなAIツールをまとめた場所です。

I only share a tiny percentage of the news that I come across in these videos.

これらのビデオで共有するニュースは、私が見つけたニュースのごく一部です。

All the rest of the news I come across, I keep up to date on the news page.

私が見つけた他のすべてのニュースは、ニュースページで最新情報を更新しています。

And there is a free AI newsletter here where I'll send you just the coolest tools I come across, just the most important news.

ここには無料のAIニュースレターがあり、私が見つけた最もクールなツールや最も重要なニュースをお送りします。

And when you sign up, I'll give you free access to the AI income database, a database of interesting fun ways to start a side hustle and make money using AI.

そして、サインアップすると、AI収入データベースへの無料アクセスを提供します。これは、AIを使用して副業を始めてお金を稼ぐための興味深い楽しい方法が記載されています。

You can find all of that at futuretools.io.

すべては futuretools.io で見つけることができます。

Thank you so much again for tuning in.

お時間を割いていただき、本当にありがとうございます。

If you like videos like this and you want to stay looped in on the news and the latest tools, make sure you like this video and subscribe to this channel.

もし今回のような動画が好きで、最新のニュースやツールについて常に情報を得たいと思うなら、この動画にいいねをしてチャンネルを購読してくださいね。

I will make sure to keep you in the loop and make sure more videos like this show up in your YouTube feed.

あなたを常に最新情報に保ち、このような動画があなたのYouTubeフィードに表示されるようにします。

And thank you once again to HubSpot for sponsoring this video.

そして、この動画のスポンサーであるHubSpotに再度感謝します。

You guys rock.

皆さん、最高です。

Appreciate you all.

皆さんに感謝しています。

See you in the next video.

次の動画でお会いしましょう。

Bye bye.

さようなら。


この記事が気に入ったらサポートをしてみませんか?