??看看Greg Brockman,President and Co-Founder of OpenAI全程演示都說(shuō)了什么~

Honestly, it's kind of hard for me to believe that this day is here. OpenAI has been building this technology really since we started the company, but for the past two years, we've been really focused on delivering GPT-4. That started with rebuilding our entire training stack（意思是重新構(gòu)建整個(gè)機(jī)器學(xué)習(xí)模型訓(xùn)練的技術(shù)和基礎(chǔ)設(shè)施。這個(gè)過(guò)程可能涉及升級(jí)硬件、軟件和流程，以提高訓(xùn)練過(guò)程的速度、效率和準(zhǔn)確性）, actually training the model, and then seeing what it was capable of, trying to figure out its capabilities（能力，"Ability" 更側(cè)重于個(gè)體的潛力和獨(dú)特性，而 "Capability" 更強(qiáng)調(diào)一種更廣泛的能力、知識(shí)和技術(shù)）, its risks, working with partners in order to test it in real-world scenarios, really tuning its behavior, optimizing the model, getting it available so that you can use it.

And so today, our goal is to show you a little bit of how to make GPT-4 shine, how to really get the most out of it（盡可能充分利用）, you know, where its weaknesses are, where we're still working on it, and just how to really use it as a good tool, a good partner.?

第一個(gè)案例：文本總結(jié)與合成

So the first thing I want to show you is the first task that GPT-4 could do that we never really got 3.5 to do. And the way to think about this is all throughout training, you know, you're constantly doing all this work. It's 2 a.m, the pager goes off, you fix the model, and you're always wondering, is it gonna work? Is all this effort actually going to pan out（work out or succeed）? And so we all had a pet task（"a pet task" 是一個(gè)英語(yǔ)習(xí)語(yǔ)，表示一個(gè)人喜歡做的、個(gè)人特別關(guān)注的任務(wù)或項(xiàng)目，通常是因?yàn)樗c個(gè)人的興趣、技能或價(jià)值觀相關(guān)。這個(gè)詞組中的 "pet" 一詞表示 "寵物"，暗示了這個(gè)任務(wù)或項(xiàng)目是像寵物一樣被人們照顧和關(guān)注的。這個(gè)詞組通常用于形容一個(gè)人在工作或?qū)W習(xí)中的任務(wù)或項(xiàng)目，也可以用于形容一個(gè)人在日常生活中的愛(ài)好或興趣。）?that we really liked and that we would all individually be trying to see, is the model capable of it now?

The way that it works is you have a system message where you explain to the model what it's supposed to do, and we've made these models very steerable（可以被控制或操縱的，eg：This video game controller features highly responsive and steerable joysticks for precise gameplay.）, so you can provide it with really any instruction you want, whatever you dream up, and the model will adhere to it（堅(jiān)持、遵守某個(gè)規(guī)定、計(jì)劃或決定） pretty well. And in the future, it will get increasingly powerful at steering the model very reliably.（未來(lái)，模型的控制系統(tǒng)將變得越來(lái)越強(qiáng)大，并且能夠非常可靠地操縱模型）?

All right. So now, time to actually show you the task that I'm referring to. So everyone's familiar with "summarize this article into a sentence," okay, getting a little more specific, but where every word begins with G. So this is 3.5, let's see what it does.

Yeah, it kind of didn't even try, just gave up on the task. This is pretty typical for 3.5 trying to do this particular kind of task. If it's, you know, sort of a very kind of stilted article（寫(xiě)作語(yǔ)言和風(fēng)格過(guò)于正式、生硬或不自然的文章） or something like that, maybe it can succeed, but for the most part, 3.5 just gives up. But let's try the exact same prompt, the exact same system message in GPT-4.?

So, kind of borderline（含糊不清的） whether you want to count AI or not, but let's say AI doesn't count. That's cheating, so fair enough. The model happily accepts my feedback.?

（接下來(lái)還試了A，Q開(kāi)頭，過(guò)程略）

All right, so I've shown you summarizing an existing article. I want to show you how you can flexibly combine ideas between different articles. So, I'm going to take this article that was on Hacker News yesterday, copy-paste it into the same conversation so it has all the context of what we're just doing. I'm going to say, find one common theme between this article and the GPD4 blog.

So, this is an article about Pinecone, which is a Python web app development framework, and it's making the technology more accessible, user-friendly（易于使用，用戶友好）. If you don't think that was insightful（有深刻見(jiàn)解的） enough, you can always give some feedback and say that was not insightful enough. Please, no, I'll just even leave it there, leave it up to the model to decide.

So, bridging the gap between powerful technology and practical applications seems not bad. And of course, you can ask for any other kind of task you want. Using its flexible language understanding and synthesis（語(yǔ)言理解和合成能力）, you can ask for something like, now turn the GPD4 blog post into a rhyming poem（韻律詩(shī)）.

So, there we go. This is consuming existing content using GPT4 with a little bit of creativity on top.?（加入點(diǎn)創(chuàng)造力）

第二個(gè)案例：代碼生成，寫(xiě)了一個(gè)能接受圖片和文字信息輸入的Discord bot

But next, I want to show you how to build with GPT4. What it's like to create with it as a partner. And so, the thing we're going to do is we're going to actually build a Discord bot.

I'll build it live and show you the process, show you debugging（調(diào)試）, show you what the model can do, where its limitations are, and how to work with them in order to sort of achieve new heights（達(dá)到新高度：reach new levels of success, excellence, or accomplishment that surpass what has been previously achieved）.?

So, the first thing I'll do is tell the model that this time it's supposed to be an AI programming assistant. Its job is to write things out in pseudocode（偽代碼） first and then actually write the code.And this approach is very helpful so that the model breaks down the problem into smaller pieces.（分解問(wèn)題）

pseudo-是假的偽的，eg：pseudonym，筆名，she's written adult fiction under a pseudonym.

pseudocode指的是一種高級(jí)抽象層次的描述性程序設(shè)計(jì)語(yǔ)言，它不是任何特定編程語(yǔ)言的實(shí)現(xiàn)，而是一種與計(jì)算機(jī)無(wú)關(guān)的通用描述方法。它是一種類似于自然語(yǔ)言的表示方法，可用于描述程序的算法或邏輯流程。使用pseudocode的好處是可以讓程序員更容易地思考和設(shè)計(jì)算法，并且可以跨越不同的編程語(yǔ)言和計(jì)算機(jī)體系結(jié)構(gòu)進(jìn)行實(shí)現(xiàn)。同時(shí)，pseudocode也可以作為編寫(xiě)代碼前的預(yù)備工作，幫助程序員更好地規(guī)劃代碼的架構(gòu)和結(jié)構(gòu)。

And then, that way, you're not kind of asking it to just come up with a super hard solution to a problem all in one go. It also makes it very interpretable（可判斷的） because you can see exactly what the model was thinking, and you can even provide corrections if you'd like.

So, here is the prompt that we're going to ask it. This is the kind of thing that 3.5 would totally choke on（卡住，難以應(yīng)對(duì)） if you've tried anything like it. But, so, we're going to ask for a Discord bot that uses the GPT-4 API to read images and texts.

Now, there's one problem here, which is this model's training cutoff（通常指機(jī)器學(xué)習(xí)模型所使用的訓(xùn)練數(shù)據(jù)的截止日期） is in 2021, which means it has not seen our new chat completions format. So, I literally just went to the blog post from two weeks ago, copy-pasted from the blog post, including the response format. It has not seen the new image extension to that, and so I just kind of wrote that up, and you know, just very minimal detail about how to include images. So, now, the model can actually leverage the documentation that it did not have memorized that it does not know.（提供了一些新的信息，使模型能夠更好地理解如何在文本中包含圖片）

And, in general, these models are very good at using information that it's been trained on in new ways and synthesizing new content. And, you can see that right here, that it actually wrote an entirely new bot.

Now, let's actually see if this bot is going to work in practice. So, you should always look through the code to get a sense of what it does. Don't run untrusted code from humans or from AIs.

And, one thing to note is that the Discord API has changed a lot over time, and particularly that there's one feature that has changed a lot since this model was trained.

Give it a try. In fact, yes, we are missing the "intents" keyword. This is something that came out in 2020.

So the model does know it exists, but it doesn't know which version of the Discord API we're using. So, are we out of luck? Well, not quite. We can just simply paste the error message to the model. We're not even going to say, "Hey, this is from running your code. Could you please fix it?" We'll just let it run.

And the model says, "Oh yeah, whoops! The 'intense' argument here's the correct code." Now, let's give this a try again, making sure that we understand what the code is doing.

//這里遇到了第二個(gè)問(wèn)題，AI 不知道代碼運(yùn)行的環(huán)境

Now, a second issue that can come up is that it doesn't know what environment I'm running in. If you notice, it says, "Hey, here's this inscrutable error message（難以理解的錯(cuò)誤信息；inscrutable：impossible to understand or interpret）," which, if you've not used Jupyter Notebook a lot with AsyncIO before, you probably have no idea what this means. But fortunately, once again, you can just sort of say to the model, "Hey, I am using Jupiter and would like to make this work. Can you fix it?"（//是我這種菜鳥(niǎo)的福音了哈哈^_^）

So now we'll run, and it looks like something happened.?

第三個(gè)案例：對(duì)圖像的描述

The first thing I'll do is go over to our Discord and I will paste in a screenshot of our Discord itself.

So, remember, GPT-4 is not just a language model, it's also a vision model. In fact, it can flexibly accept inputs that intersperse images and text arbitrarily, kind of like a document.（GPT-4 的新特性：它不僅僅是一個(gè)語(yǔ)言模型，還可以處理圖像和文本混合的輸入，就像處理文檔一樣）

Now, the image feature is in preview（預(yù)演階段）, so this is going to be a little sneak peek（偷看，提前看）. It's not yet publicly available（公開(kāi)）. It's something we're working with one partner called Be My Eyes in order to really start to develop it and get it ready for prime time. （面向廣大用戶使用，prime time：廣播電視的黃金時(shí)段）

But you can ask anything you like. For example, I can say, "GPT-4, hello world, can you describe this image in painstaking detail（詳細(xì)的描述）?" Alright, which, first of all, think of how you would do this yourself. There are a lot of different things you could latch onto（抓?。?/span>, a lot of different pieces of the system you could describe.?

So it's a screenshot of a Discord application interface. Pretty good, didn't even describe it, it knows that it's Discord. It's probably Discord written there somewhere where it just kind of knows this from prior experience. Server icon label GPT4 describes the interface in great detail, talks about all the people telling me that I'm supposed to do Q, a very, very kind audience, and describes much of the notification messages and the users that are in the channel. And so there you go, that's some pretty good understanding.

（后面又解了一個(gè)bug，過(guò)程略。。）

I think this augmenting tool makes you much more productive, but it's still important that you are in the driver's seat and are the manager and knows what's going on.

（工具雖強(qiáng)，人還是要做主導(dǎo)）

Squirrels do typically eat nuts. We don't expect them to use a camera or act like a human, so I think that's a pretty good explanation of why that image is funny. So, I'm going to show you one more example of what you can do with this model.

第四個(gè)案例：根據(jù)原型圖生成網(wǎng)頁(yè)

So, I have here a nice hand-drawn mock-up of a joke website, definitely worthy of being put up on my refrigerator. So, I'm just going to take out my phone, literally take a photo of this mock-up, and then I'm going to send it to our Discord.

All right, I'm going to send it to our Discord, and this is, of course, the rockiest part（一個(gè)過(guò)程中最具挑戰(zhàn)性、最艱難的階段）: making sure that we actually send it to the right channel, which, in fact, I think maybe I did not send it to the wrong channel. It's funny; it's always the non-AI parts of these demos that are the hardest part to do.? And here we go, technology is now solved, and now we wait.

So, the thing that's amazing in my mind is that what's going on here is we're talking to a neural network, and this neural network was trained to predict what comes next. It played this game of being shown a partial document and then predicted what comes next across an unimaginably large amount of content.??

（神經(jīng)網(wǎng)絡(luò)被訓(xùn)練用于預(yù)測(cè)下一個(gè)可能出現(xiàn)的內(nèi)容。它通過(guò)對(duì)大量?jī)?nèi)容進(jìn)行訓(xùn)練，模擬了在看到部分文檔內(nèi)容后預(yù)測(cè)接下來(lái)會(huì)出現(xiàn)什么的過(guò)程）

And from there, it learns all of these skills that you can apply in all these very flexible ways. And so, we can actually take now this output, so literally we just said to output the HTML from that picture, and here we go, actual working JavaScript filled in the jokes?

This was the original of our mock-up, and so there you go, going from hand-drawn beautiful art, if I do say so myself, to a working website. And this is all just potential, right??

You can see lots of different applications. We ourselves are still figuring out new ways to use this, so we're going to work with our partner. We're going to scale up（擴(kuò)大、增加或提高規(guī)模、范圍或數(shù)量） from there, but please be patient because it's going to take us some time to really make this available for everyone.

one last thing：處理報(bào)稅問(wèn)題

So, I have one last thing to show you. I've shown you reading existing content, I've shown you how to build with the system as a partner. The last thing I'm going to show is how to work with the system to accomplish a task that none of us like to do but we all have to. So, you may have guessed the thing we're going to do is taxes.

Now, note that GPT is not a certified tax professional（美國(guó)報(bào)稅異常復(fù)雜，所以會(huì)有專業(yè)的稅務(wù)師）, nor am I, so you should always check with your Tax Advisor. But it can be helpful to understand some dense content（復(fù)雜的內(nèi)容：material that is difficult to understand or requires a lot of effort to comprehend） to just be able to empower yourself to（賦能哈哈） solve problems and get a handle on?（可以去處理to understand and be able to deal with ）what's happening when you could not otherwise.

So once again, I'll do a system message. In this case, I'm going to tell it that it's tax GPT, which is not a specific thing that we've trained into this model. You can be very creative if you want with the system message to really get the model in the mood of?（在...情景下）what is your job, what are you supposed to do.

So, I pasted in the tax code. This is about 16 pages worth of tax code, and there's this question about Allison and Bob. They got married at one point, and here are their incomes, and they take a standard deduction（指的是可以從納稅人的總收入中減去的固定金額，以確定納稅人應(yīng)該繳納的可征稅收入）. They're filing jointly. So first question: what is their standard deduction for 2018?

If you notice, the model got to the same conclusion, and you can actually read through its explanation. And to tell you the truth, the first time I tried to approach this problem myself, I could not figure it out. I spent half an hour reading through the tax code, trying to figure out this back reference and why there's some program like just what's even going on. It was only by asking the model to spell out its reasoning, and then I followed along, that I was like, oh, I get it now.?

I understand how this works. And so that I think is where the power of the system lies. It's not perfect, but neither are you, and together is this amplifying tool that lets you just reach new heights, and you can go further.?

（它并不完美，但你也不完美，而使用它就像一個(gè)放大器，讓你可以達(dá)到新的高度，你可以走得更遠(yuǎn)）

And so to end it, the final thing that I will show is a little other dose of creativity, which is now summarize this problem into a rhyming poem. And there we go, a beautiful, beautiful poem about doing your taxes.?

So thank you everyone for tuning in！