Name: GPT-4讓舊的ChatGPT看起來像個笑話! (GPT-4 Makes Old ChatGPT Look Like a JOKE!)
Uploaded: 2023-03-16T09:30:32.000Z
Duration: 12 min 56 s

情態副詞

This basically eliminates the need of having some middle or junior developer doing the work for you.

這基本上消除了讓一些中級或初級開發人員為你做工作的需要。

情態助動詞 B1

And in many cases, this might actually be faster and more efficient than that developer.

而在許多情況下，這實際上可能比那個開發者更快、更有效。

I'm going to try the brand new GPT four model that was just released by OPEN AI in chat GPT.

我打算試試OPEN AI剛剛發佈的全新的GPT四號模型，在哈拉GPT中。

Now I am a chat GPT plus member so I can already use it as you can see it is an option in this dropdown.

現在我是一個哈拉的GPT plus會員，所以我已經可以使用它了，你可以看到它是這個下拉菜單中的一個選項。

I just woke up to the announcement and I'm walking into this blind.

我剛剛被宣佈的消息驚醒，我正在盲目地走入這個世界。

The previous video I made on chart G B T with the old model was impressive, but at the time of recording had already tried the model, knew what it could, it could not do.

我之前用舊模型製作的圖表G B T的視頻令人印象深刻，但在錄製時已經試過這個模型，知道它能做什麼，它不能做什麼。

And I had to try many, many times until it eventually got to the right answers.

而且我不得不嘗試很多很多次，直到最終得到正確的答案。

Needless to say it wasn't great in this video.

不用說，在這段視頻中它並不出色。

I will only give it a single chance and I have a set of questions.

我只給它一次機會，我有一組問題。

I want to ask it both in software engineering and solution architecture and scribe the questions that both junior mid and senior developers would need to answer as part of the day job.

我想在軟件工程和解決方案架構中都提出這個問題，並記錄下初級中級和高級開發人員作為日常工作的一部分需要回答的問題。

If you like to have content, you want to see more, make sure you subscribe during the solidification bell and formal training, check out nick chapters dot com.

如果你喜歡有內容，你想看到更多的內容，請確保你在固化鍾和正式培訓期間訂閱，請查看Nick chapters dot com。

是以，讓我們看看我們這裡有什麼。

So we have these three models, right, the default, which is supposed to be fair and turning very fast and not really concise.

是以，我們有這三種模式，對，默認的，應該是公平的，而且轉得非常快，並不是真的簡潔。

Then you have the legacy model which I don't know if it was the original GPT or not, but it seems to be a previous charge GPT plus model which has different characteristics.

然後你有一個傳統的模型，我不知道它是否是最初的GPT，但它似乎是以前的收費GPT plus模型，具有不同的特點。

And then GPT forwards supposed to be the most advanced where you have excellence in reasoning and conciseness, but it's not as fast and we're gonna use that.

然後GPT向前應該是最先進的，在那裡你有卓越的推理和簡潔，但它沒有那麼快，我們要用這個。

So the first thing I see here is that there's a cap of one 100 messages for every four hours.

是以，我在這裡看到的第一件事是，每四個小時有一個100條資訊的上限。

So I guess they rate limited because of how much computation sha li intense.

所以我猜他們的評價是有限的，因為有多少計算sha li激烈。

It is what I'm going to ask it as the first question is, please create a rest API with C shop and dot net six that allows users to create read update and delete movies and also rate them think Rotten Tomatoes or IMDB and API for those things where you can list the movie and rate it and then use prosperous for the database.

這是我要問的第一個問題，請用C店和dot net six創建一個rest API，允許用戶創建、閱讀、更新和刪除電影，也可以對它們進行評價，想想Rotten Tomatoes或IMDB和API的那些東西，你可以列出電影和評價它，然後用旺財做數據庫。

And then framework for the data access anti framework is like an R M in dot net.

然後，用於數據訪問的反框架就像點網絡中的R M。

是以，讓我們看看你能用它做什麼。

So straight away, just like before we have the same stream response and I would say it's equally as slow.

是以，直接就像以前一樣，我們有相同的流響應，我想說它同樣緩慢。

So let's wait and see what it spits out so far.

是以，讓我們拭目以待，看看到目前為止它吐出了什麼。

So good, everything here is things I would do.

太好啦，這裡的每一件事都是我要做的事。

So we have the settings, we get the whole file previously.

是以，我們有設置，我們之前得到了整個文件。

Sometimes you would only get the line you need to add, you have the model and it is using anti framework which allows you to have nested objects that point into other objects and generated database on demand.

有時你只會得到你需要添加的行，你有模型，它使用反框架，允許你有嵌套對象，指向其他對象，並按要求生成數據庫。

Then it knows to make a movie DB context as well, movies and ratings great.

然後它知道讓電影DB的背景也是如此，電影和收視率很大。

Now it's going to use the startup dot CS, which we don't really use anymore in C shop.

現在它要使用啟動點CS，我們在C店已經不怎麼使用了。

But given when this was trained, this was very much relevant.

但考慮到這是在什麼時候訓練的，這是很有意義的。

Now, one of the things I wouldn't do in that startup dot CS is run migrations there and would actually have them in the program dot CS.

現在，我不會在那個啟動點CS中做的事情之一是在那裡運行遷移，實際上會在程序點CS中進行遷移。

But that is not a huge mistake at say or it goes straight away into using a controller.

但這並不是一個巨大的錯誤，或者說它直接進入了使用控制器。

It injects the DB context and then it uses a sing programming properly.

它注入了DB上下文，然後它正確地使用了一個sing編程。

哦，這對更新電影來說是令人印象深刻的。

It also handles DB, update concurrency exceptions which many people would actually forget to cover.

它還可以處理DB、更新併發的異常情況，很多人實際上會忘記涉及這些問題。

And then it knows to name things like the routes appropriately as the rest API should, which is the plural of the entity you're trying to deal with or the results you're trying to deal with and then it correctly points to the action that is supposed to give you the location header to indicate that on movie creation, that's where you can find your movie.

然後它知道適當地命名一些東西，比如路由，就像其他API應該的那樣，這是你試圖處理的實體或你試圖處理的結果的複數，然後它正確地指向應該給你位置頭的行動，以表明在電影創建時，這是你可以找到你的電影的地方。

So that's really, really impressive and fantastic.

是以，這真的是非常，非常令人印象深刻和奇妙。

In the end, we also get an explanation like a documentation of every I'm gonna tell you what except for the thing where I had to explicitly say continue when the thing stopped.

最後，我們也得到了一個解釋，就像每一個我要告訴你什麼的文件一樣，除了在事情停止的時候我必須明確說繼續。

This is a perfectly valid response that you can actually use and you wouldn't be in any way wrong.

這是一個完全有效的迴應，你可以實際使用，你不會有任何錯誤。

But you're walking into more opinionated round.

但你正在走進更多有意見的回合。

So this is one of the most generic way you can do that and it's absolutely fine and it's the first try.

是以，這是你可以做到的最通用的方法之一，而且絕對沒問題，這也是第一次嘗試。

Alright, let's see how you can make it go further.

好吧，讓我們看看你如何能讓它更進一步。

One of the biggest problems with this is that the connection string is a Rasta ring with passwords and user names as plain text in the app settings dot Jason file.

這方面最大的問題之一是，連接字符串是一個拉斯特環，密碼和用戶名在應用程序設置點Jason文件中是純文本。

Usually what you do is you would actually use the secrets manager like key vault or AWS Secrets manager or you would load them as environment variables scope to that specific service.

通常你要做的是，你實際上會使用祕密管理器，如鑰匙庫或AWS祕密管理器，或者你會將它們作為環境變量加載到該特定服務的範圍。

So what I want to ask it is whatever developer might ask.

是以，我想問的是，無論開發人員可能問什麼。

Hey, so my mate said that having connection strings in the settings as clear text is a bad practice.

嘿，我的朋友說，在設置中把連接字符串作為明文是一種不好的做法。

Any suggestions on how to make that more secure.

有沒有關於如何使之更安全的建議。

Let's see what says your mate is correct.

讓我們看看什麼說你的伴侶是正確的。

So it acknowledges that it is not secure and it suggests secret managers like key vault or other tools.

是以，它承認它是不安全的，它建議祕密管理器，如鑰匙庫或其他工具。

Interesting that it is as biased and I didn't get any other suggestions like an Aws ones.

有趣的是，它是有偏見的，我沒有得到任何其他建議，如Aws的建議。

So for local development use secret manager tool and what am I supposed to use for production?

那麼，在在地開發中使用祕密管理器工具，在生產中我應該使用什麼？

It is not wrong as long as there is scope to the thing that's loading them.

只要加載它們的東西有範圍，那就沒有錯。

And it also suggests as our key vault and it gives me the code.

它還建議作為我們的關鍵金庫，它給了我密碼。

I'm wondering if the Microsoft money make it be more Azra biased than Aws biased.

我在想，微軟的資金是否使它更偏向於Azra而不是Aws。

I'm gonna go a bit of the scripted quest just because I want to see if it can do this with Aws as well.

我打算走一點腳本式的追求，只是因為我想看看它是否也能用Aws做這個。

Actually, we are using Aws in my company and I'm just gonna tell you that in the previous Oh my God straightaway Aws Secrets Manager.

實際上，我們公司正在使用Aws，我只是要告訴你，在前面的哦，我的上帝直接Aws祕密管理器。

In the previous video I had to really guided and really put things into context for it to actually give good results.

在之前的視頻中，我必須真正地引導，真正地把事情放到背景中去，才能真正給出好的結果。

This just goes into, hey, here's the documentation read about Secrets Manager at the new package.

這只是進入了，嘿，這裡的文檔是在新的包裡讀到的關於祕密管理器。

And I've noticed it goes way more in depth into the thing it is talking about the previous matter.

而且我注意到，它對它所談論的事情的深入程度遠遠超過了前一個問題。

We'll just give you way less text and basically telling you for the rest.

我們只是給你更少的文字，其餘的基本上都是在告訴你。

我們得到的一切實際上是堅果。

I, I have no words, Jesus, the detail that goes into even Windows specific and then I guess Linux or Mac specific settings like these are right things if I copy this, it will take me to my credentials, file for ws this is nuts.

我，我無話可說，天哪，即使是Windows的具體細節，然後我想Linux或Mac的具體設置，如這些是正確的事情，如果我複製這個，它會帶我到我的證書，文件為ws，這是堅果。

What if I want integration tests, write integration tests for the API using the web publication factory?

如果我想進行集成測試，使用網絡發佈工廠為API編寫集成測試，怎麼辦？

The reason why I'm so excited about this is this will save me so much time.

我之所以如此興奮，是因為這將為我節省大量的時間。

There is so much code I and many developers, I'm sure have to write.

我和許多開發者，肯定有很多代碼要寫。

That is like this, that to a degree is roughly the same but not exactly the same.

這就像這樣，在某種程度上是大致相同的，但不完全相同。

So based on how good they say it's gonna save me so much time and it makes the money I pay for LGBT plus, we're actually worth it.

是以，基於他們說的有多好，它能為我節省這麼多時間，它使我為LGBT支付的錢加上，我們實際上是值得的。

And here's what I think about this up until now.

下面是我到現在為止對這件事的看法。

When people were asking me, will this replace people's jobs?

當人們問我，這是否會取代人們的工作？

You still someone who knows enough to babysit it and review things.

你仍然有人知道，足以照看它和審查事情。

But thinking about this, I can totally see someone making a tool that a developer and actual developer can go into a GIT repo create an issue.

但考慮到這一點，我完全可以看到有人制作一個工具，讓開發人員和實際的開發人員可以進入GIT repo創建一個問題。

You say that's what the issue is, go fix it.

你說這就是問題所在，去解決吧。

Then a charge GPT bought using the A P I can go in read the issue act and then create a pull request and then it's just the developer reviewing the pull request and charge GPT fixing it automatically as you go.

然後，使用A P I購買的收費GPT可以進入閱讀問題的行為，然後創建一個拉動請求，然後只是開發人員審查拉動請求，收費GPT在進行時自動修復它。

So I'm a bit skeptical and scared everything it said in principle here is correct.

所以我有點懷疑，害怕它在這裡所說的一切原則性的東西是正確的。

I'm pretty sure I can ask you to say add more tests and it can do that for me.

我敢肯定，我可以要求你說添加更多的測試，它可以為我這樣做。

Now, would I validate here for headers like this specific header?

現在，我是否會在這裡對像這個特定的標題進行驗證？

I wouldn't, I would check for the response and see that the object is what I wanted to be.

我不會，我會檢查反應，看對象是否是我想成為的。

So it is not awesome but it gives you a framework to work on.

是以，它並不可怕，但它給了你一個工作的框架。

字幕列表影片播放

GPT-4讓舊的ChatGPT看起來像個笑話! (GPT-4 Makes Old ChatGPT Look Like a JOKE!)

specific

absolutely

approach

context