Name: 今天人人都能使用的新人工智能工具 (New AI Tools Anyone Can Use Today)
Uploaded: 2024-06-24T12:56:55.000Z
Duration: 16 min 41 s

祈使句型

All right, so look, if you follow this weekly show, you know I don't say this lightly.

好吧，聽著，如果你關注這個每週節目，你就知道我不會輕易說這些。

未來簡單式

I believe in this week's edition, there's going to be a use case with AI for everybody watching this video.

我相信，在本週的版本中，每個觀看視頻的人都會看到一個人工智能的用例。

頻率副詞

And that's a big claim, because most people don't even use AI regularly.

這是一個很大的挑戰，因為大多數人根本不會經常使用人工智能。

But I believe this week is so colorful in terms of different applications, that even the AI haters will find something they might want to try.

但我相信，本週的不同應用是如此豐富多彩，即使是憎恨人工智能的人也會找到他們想嘗試的東西。

Because we do have a brand new chat GPT feature, we have to talk about that.

因為我們確實有一個全新的哈拉 GPT 功能，我們必須談談這個功能。

And then the best in class image generator, Midjourney, finally is rolling out the alpha access to the website to almost all users.

然後，一流的圖片生成器 Midjourney 終於向幾乎所有用戶推出了網站的 alpha 訪問權限。

But beyond that, there's the specialty websites where you can try on clothes or create virtual avatars that should be interesting to people that don't even use this in their everyday workflow.

但除此之外，還有一些專業網站可以讓你試穿衣服或創建虛擬化身，這對那些在日常工作流程中根本不使用這些功能的人來說應該會很有趣。

So without further ado, let's dive into this week's AI news you can use.

話不多說，讓我們來看看本週的人工智能新聞。

Okay, first things first, chat GPT update memory.

I almost created a separate video on this, but then I played with it for a few hours.

我差點就此製作一個單獨的視頻，但後來我又玩了幾個小時。

I was like, this is going to be a segment in the weekly news show.

我當時想，這一定會成為每週新聞節目的一個環節。

And that's it, because it's not as revolutionary as many people make it out to be.

就是這樣，因為它並不像很多人說的那樣具有革命性。

Well, let me give you a super quick summary, and then I'll give you some tips on how to actually get something out of this feature.

好吧，讓我給你一個超級快速的總結，然後我會給你一些提示，告訴你如何真正從這個功能中獲得一些東西。

So basically, they have a new feature here where you can go to settings, personalization, memory.

所以基本上，他們在這裡有一個新功能，你可以進入設置、個性化、記憶。

Now, if you're in Europe or South Korea, you don't get this feature.

現在，如果你在歐洲或韓國，就無法使用這項功能。

And if you have a Teams or Enterprise account, you don't get this feature.

如果你擁有團隊或企業賬戶，則無法使用此功能。

Let me tell you, me as somebody who sits in Europe and has a chat GPT Teams account for the entire AI Advantage team, I was not pleased to hear this at all.

讓我告訴你，我作為一個身在歐洲併為整個 AI Advantage 團隊開設了 GPT 團隊哈拉賬戶的人，聽到這個消息一點也不高興。

So I had to create a brand new one and use a VPN to tell my browser I'm in the US.

是以，我不得不創建一個全新的，並使用 VPN 告訴我的瀏覽器我在美國。

And that's why I have access to it over here.

這也是我能在這裡使用它的原因。

It comes turned off by default, and it's basically automatically generated custom instructions for all of your chat GPT for usage, meaning this is a beginner feature.

默認情況下它是關閉的，而且基本上是自動為所有哈拉 GPT 生成自定義使用說明，這意味著這是一項初級功能。

If you've been creating your custom instructions manually, as I've been teaching on this channel since the day they released, you should know the power of adding context to all of your prompts.

如果你一直在手動創建自定義說明，就像我從發佈之日起就在本頻道教授的那樣，你應該知道為所有提示添加上下文的強大功能。

So look, I had some conversations with it.

所以，你看，我和它進行了一些對話。

I mentioned that my boss's name is Karen.

And then I had it store my style and my name.

然後，我就用它來儲存我的風格和我的名字。

And it simply does this by picking up on some conversations you have with it here, okay?

它只是通過你與它在這裡的一些對話來做到這一點，好嗎？

So as you can see, you can have a conversation here.

是以，正如您所看到的，您可以在這裡進行對話。

And as you go back and forth, you can say something like, great, store details about my preferences and feedback in memory.

當你來來回回時，你可以說："很好，把我的喜好和反饋的細節存儲在內存中。

What I did up here is I just fed it all my custom instructions like I teach them on the channel.

我在這裡所做的，就是像我在頻道上教他們的那樣，給它輸入我所有的自定義指令。

It's probably the most important video on ChatGPT that you should check out.

這可能是 ChatGPT 上最重要的視頻，你應該看看。

But basically, I fed it my custom instructions, and then it stored them to memory.

但基本上，我向它輸入了我的自定義指令，然後它就會把這些指令存儲到內存中。

So they're a natural language instead of bullet points.

是以，它們是一種自然語言，而不是要點。

But pretty much, it's the preset I have in custom instructions all the time.

但實際上，這是我在自定義指令中一直使用的預設值。

Again, in some other videos, I teach you how to set these up for yourself.

同樣，在其他視頻中，我會教你如何為自己設置這些功能。

We have had custom instructions since a while.

他們做的事情和這個是一樣的。

現在，聽著，有一點是不同的。

I know there's going to be somebody in the comments pointing out, but hey, Igor, this history feature doesn't work exactly like custom instructions.

我知道會有人在評論中指出，但伊戈爾，這個歷史功能並不完全像自定義說明那樣工作。

It creates an embedding that is stored in a vector database.

它創建的嵌入資訊存儲在矢量數據庫中。

That's why it doesn't add to your context window just like custom instructions do.

這就是為什麼它不會像自定義指令那樣添加到上下文窗口中。

And while that is true, what is inside your memory doesn't count as a part of the limited context window.

雖然這是事實，但你記憶中的東西並不算是有限語境窗口的一部分。

There's no confirmation whatsoever that this is using a vector database.

沒有任何證據表明它使用的是矢量數據庫。

At the end of the day, a few tokens are not going to change the game for you with the custom instructions.

歸根結底，幾枚代幣並不能改變遊戲中的自定義指令。

We have a 32k context limit with GPT-4 these days.

目前，我們的 GPT-4 有 32k 上下文限制。

Anything you want it to retain, you can just put into the custom instructions and keep it there without having to worry about the fact that ChatGPT might just pick up some context here and there and add it to your history.

您想讓它保留的任何內容，都可以直接放入自定義說明並保留在那裡，而不必擔心 ChatGPT 可能會在這裡或那裡獲取一些上下文，並將其添加到您的歷史記錄中。

I mean, what if you're prompting something for work and then you're maybe creating a trivia quiz for the birthday party of your child?

我的意思是，如果你是在為工作提示信息，然後又為孩子的生日派對創建一個瑣事問答，那該怎麼辦？

You don't want your work context to infect that generation.

你不希望你的工作環境感染那一代人。

So to anybody who's a little more advanced, aka if you're watching this channel, you're probably at that level.

是以，對於稍微高級一點的人來說，也就是如果你正在收看這個頻道，你可能已經達到了這個水準。

I still recommend using custom instructions.

Now, look, where this does get interesting is something that they announced for the future, but that's simply not the fact today.

現在，聽著，這確實很有趣，因為他們宣佈了未來的計劃，但今天的事實根本不是這樣。

They announced that GPTs are going to have localized history.

他們宣佈，GPT 將擁有本地化的歷史。

So as you use a GPT, it's going to pick up a piece of context, store it to the local history of that GPT.

是以，當你使用 GPT 時，它會獲取一段上下文，並將其存儲到該 GPT 的在地歷史記錄中。

You want that because the GPT is context specific.

之所以要這樣做，是因為 GPT 是針對具體情況的。

But using ChatGPT, not context specific, use it for all sorts of things.

但使用 ChatGPT 時，並沒有特定的上下文，可以用來做各種各樣的事情。

So in summary, I think this feature makes a lot of sense for GPTs.

總之，我認為這項功能對 GPT 非常有意義。

It might be a great addition for newcomers that have no idea that custom instructions exist and that you can put your preferences in there.

對於不知道有自定義說明存在，也不知道可以把自己的喜好寫進去的新手來說，這可能是一個很好的補充。

But for anybody watching this channel, chances are you're better off using custom instructions as of now.

但對於觀看本頻道的人來說，現在最好還是使用自定義說明。

And with that being said, let's move on to the next one.

說完這些，我們繼續下一個話題。

這是一個非常有趣的應用程序。

它叫 AnyTopic，目前處於測試階段。

And look, this is not something revolutionary, but it's really cool.

聽著，這不是什麼革命性的東西，但它真的很酷。

And at the time of this recording, it's free.

在錄製本節目時，它是免費的。

You can go in here and you can pick one of these categories.

您可以在這裡選擇其中一個類別。

What it does is it turns anything into an audiobook that you can then listen to.

它可以將任何內容轉化為有聲讀物，然後您就可以收聽了。

So for example, I could go in here and say, hey, I want an audiobook for my commute.

例如，我可以在這裡說，嘿，我想在上下班途中聽有聲讀物。

I could set that my commute is, let's say, 15 minutes long.

比方說，我可以設定我的通勤時間為 15 分鐘。

And then I could post the article in here.

然後我就可以在這裡發表文章了。

So you might have caught these speculations about the GPT 2 chatbot that came out this week.

所以，你可能已經捕捉到了本週發佈的有關 GPT 2 哈拉機器人的這些猜測。

We're not covering that in depth because this is AI news you can use.

我們不會對此進行深入報道，因為這是你可以使用的人工智能新聞。

And as of now, you can't even use GPT 2 chatbot.

目前，您甚至無法使用 GPT 2 哈拉機器人。

The point is I have this article here and maybe I want to consume this on my commute as a audiobook and not read this right now.

重點是，我這裡有這篇文章，也許我想在上下班途中聽一聽，而不是現在就讀這篇文章。

So what you could do is you could just copy this.

You could paste the link in here and it would create, let's say, like a five-minute audiobook.

你可以在這裡粘貼鏈接，這樣就可以創建一個五分鐘的有聲讀物。

You just hit this and for free, it's going to send you an email.

你只需點擊這裡，它就會免費向你發送一封電子郵件。

Now, I actually did exactly that with a 10-minute duration.

現在，我確實做到了這一點，持續時間為 10 分鐘。

So here you can have a listen to the audiobook it created and use this narrative structure.

是以，您可以在這裡收聽它製作的有聲讀物，並使用這種敘事結構。

I'm going to skip around here a little bit so you can get a feeling.

我先在這裡跳一跳，讓你們感受一下。

但這也是一個很酷的用例，不是嗎？

Imagine stepping into an arena where titans of technology spar with words instead of weapons, showcasing their prowess in solving puzzles and answering questions with the precision of a grandmaster chess player.

想象一下，在這個競技場上，科技巨頭們以文字代替武器進行比拼，展示他們解謎的能力，像國際象棋大師一樣精準地回答問題。

好吧，所以它的介紹就像一個故事。

And then let's dive a little deeper here.

字幕列表影片播放

今天人人都能使用的新人工智能工具 (New AI Tools Anyone Can Use Today)

entire

essentially

context

content