为什么大肆宣传？ (Why the hype?)

A few weeks ago, OpenAI released GPT-3, the latest version of their language generation model. Examples of GPT-3 doing everything from writing fiction to generating working JavaScript quickly went viral, leading to widespread press coverage with headlines like, “What Is GPT-3 and Should We Be Terrified?”

几周前，OpenAI发布了GPT-3，这是他们语言生成模型的最新版本。 从编写小说到生成有效JavaScript的所有过程中，GPT-3的例子Swift传播开来，并引起了广泛的新闻报道，标题为“什么是GPT-3，我们应该害怕吗？”

Farhad Manjoo at the New York Times put it this way:

纽约时报的Farhad Manjoo 这样说 ：

I’ve never really worried that a computer might take my job because it’s never seemed remotely possible. Not infrequently, my phone thinks I meant to write the word “ducking.” A computer writing a newspaper column? That’ll be the day.

我从来没有真正担心过计算机会接任我的工作，因为它似乎永远不可能实现。 并非经常，我的手机认为我要写“ ducking”一词。 用电脑写报纸专栏吗？ 那一天。

Well, writer friends, the day is nigh. This month, OpenAI, an artificial-intelligence research lab based in San Francisco, began allowing limited access to a piece of software that is at once amazing, spooky, humbling and more than a little terrifying.

好吧，作家朋友，这一天快到了。 本月，位于旧金山的人工智能研究实验室OpenAI开始允许有限地访问一件既令人惊奇，诡异，令人毛骨悚然的软件，又不至于有点恐怖的软件。

What makes GPT-3 so good? The model was trained on a staggeringly large volume of text — according to The Verge, all of English Wikipedia makes up just 0.6% of the total dataset — and fine-tuned with 175 billion parameters. Unlike other learners, GPT-3 is able to produce fairly good output for a variety of specialized tasks without much extra training.

是什么使GPT-3如此出色？ 该模型是在大量文本上进行训练的-根据The Verge的说法，英语维基百科的全部仅占总数据集的0.6％ -并使用1,750亿个参数进行了微调。 与其他学习者不同，GPT-3无需进行过多的培训就可以针对各种专业任务产生相当不错的输出。

For now, GPT-3’s API is only accessible via a private beta. I recently got an invite and couldn’t wait to put it to the test. In particular, I was curious how the model would handle a task that required both specialized knowledge and creativity, especially in an area where I at least have a shot of judging the quality of its answers.

目前，只能通过私有Beta访问GPT-3的API。 我最近收到了邀请，迫不及待地要接受测试。 特别是，我很好奇该模型将如何处理既需要专业知识又需要创造力的任务，特别是在我至少能判断其答案质量的领域。

GPT-3的混合学 (Mixology with GPT-3)

To start GPT-3 off, I trained it with a few examples from Billy Sunday, a Chicago institution and my all-time favorite cocktail bar. I gave the model some context and listed the main ingredient, name, and recipe for a few real Billy Sunday cocktails:

要开始使用GPT-3，我从芝加哥机构Billy Sunday和我一直以来最喜欢的鸡尾酒吧中举了一些例子对它进行了培训。 我为模型提供了一些上下文，并列出了一些真正的比利周日鸡尾酒的主要成分，名称和配方：

Here are some high-end drinks on the menu at Billy Sunday, a Chicago cocktail bar.Ingredient: rumCocktail: TROPIC THUNDER — RUM BLEND, UBE ORGEAT, COCONUT, ORANGE & LIMEIngredient: tequilaCocktail: PARCHA PUNCH — REPOSADO TEQUILA, MEZCAL, PASSION FRUIT, OREGANO, LIME & SALTIngredient: ginCocktail: YERBE MATE HIGHBALL — GIN, YERBA MATE TEA & LEMON

After feeding all 7 seasonal cocktails on Billy Sunday’s menu into the API, I prompted it with a few more ingredients to see what it would come up with. GPT-3’s output is in bold:

在将Billy Sunday菜单上的所有7种时令鸡尾酒都加入API后，我提示它添加了更多成分，以查看会产生什么效果。 GPT-3的输出以粗体显示 ：

Ingredient: mezcalCocktail: EL DIABLO — MEZCAL, CINNAMON, LEMON, ORANGE, ANCHO CHILI & SALTIngredient: fernet brancaCocktail: THE BERLINER - FERNET BRANCA, GINGER, LEMON, SODA & GINGER ALEIngredient: macallanCocktail: THE MACK - MACALLAN 12YR, SWEET VERMOUTH, CHERRY HEERING, ANGOSTURA & ORANGE BITTERSIngredient: suntory whiskyCocktail: SWEET TEA - SWEET TEA-INFUSED SUNTORY WHISKY, LEMON, SUGAR & LEMON BITTERSIngredient: green chartreuseCocktail: THE GREEN EYESHADE - GREEN CHARTREUSE, BOURBON, LEMON, ORANGE & SAGEIngredient: bacon-infused bourbonCocktail: BACON NOG - BACON-INFUSED BOURBON, EGG YOLK, SWEETENED CONDENSED MILK, VANILLA, SPICES & NUTMEG

Its suggestions aren’t perfect — for example, a Berliner is already an established cocktail with gin and vermouth — but overall these drinks wouldn’t feel out of place on the menu at any trendy cocktail bar.

它的建议并不完美-例如， 柏林人已经是杜松子酒和苦艾酒的知名鸡尾酒了-但总体而言，这些饮料不会在任何时尚鸡尾酒吧的菜单上让您感到不适。

Kicking it up a notch

踢一个缺口

GPT-3’s API includes a neat parameter called temperature, a value between 0 and 1 that controls the output’s randomness. OpenAI likens it to adjusting creativity. The examples above were generated with a very low temperature, 0.1.

GPT-3的API包含一个名为temperature的整洁参数，该参数介于0和1之间，用于控制输出的随机性。 OpenAI将其比喻为调整创造力。 上面的示例是在0.1的极低温度下生成的。

When I set the temperature to 0.1 and prompted GPT-3 to make a cocktail using Pimm’s, a fruit liqueur, it made a predictable choice and pretty much suggested a standard Pimm’s Cup (though the right ingredient is ginger ale, not ginger):

当我将温度设置为0.1并提示GPT-3使用水果利口酒Pimm's制作鸡尾酒时，它做出了可以预测的选择，并且几乎建议使用标准的Pimm's Cup (尽管正确的配料是姜汁啤酒，而不是姜汁)：

Ingredient: pimm'sCocktail: PIMM'S CUP - PIMM'S NO. 1, LEMON, GINGER, LIME, CUCUMBER & SODA

After I turned up the temperature to 0.5, GPT-3 decided to add a twist on the classic cocktail:

在我将温度调到0.5之后，GPT-3决定在经典鸡尾酒上加些捻：

Ingredient: pimm'sCocktail: MELON PIMM'S CUP - PIMM'S NO. 1, FRESH MELON, LIME & LEMON

And at a temperature of 0.9, GPT-3 got really creative:

在温度为0.9的情况下，GPT-3真正发挥了创意：

Ingredient: pimm’sCocktail: THE BLENDER — PIMMS CUP #3, WHISKEY, ORANGE, LEMON, BITTERS, CUCUMBER & PINEAPPLE

Here are a few interesting recipes that GPT-3 invented with the temperature cranked up to 0.9:

这是GPT-3在温度升高到0.9时发明的一些有趣的食谱：

Ingredient: vermouthCocktail: YOU NEED AN ENGLISHMAN IN NEW YORK - OLD TOM GIN, VERMOUTH NOIR, ORANGE OIL, LICORICE TEA & ANISE HYSSOPIngredient: campariCocktail: LORETTA LEE - AVERNA, CAMPARI, CAMPARI-AGAVE SYRUP, DRY VERMOUTH & BITTER LEMONIngredient: disaronnoCocktail: STRAWBERRY COLA - DISARONNO, STRAWBERRY, KIRSCH, SODA & LEMONIngredient: brandyCocktail: LADY WINCHESTER - COGNAC, ST. GERMAIN, ORANGE & PINEAPPLEIngredient: ipaCocktail: STACK OF NICKEL - IPA, PEYCHAUD’S BITTERS, TONIC & BITTER MINT

最后的想法 (Final Thoughts)

It’s truly impressive how easily GPT-3 can generate plausible text, but it isn’t taking over the world any time soon. I cherry-picked the most interesting examples above, but the model made a lot of obvious errors. For, example, it sometimes reused the names of popular drinks or suggested entire cocktails, like “martini” or “caipirinha”, as ingredients in its creations. On rare occasions, the model even included nonsensical ingredients like “iwa kachinoki washi tango” (which it wanted to use in a Jameson-based cocktail it dubbed “Jameson and Me”).

GPT-3能够轻松生成合理的文本确实令人印象深刻，但它不会很快占领整个世界。 我挑选了上面最有趣的示例，但是该模型犯了很多明显的错误。 例如，它有时将流行饮料的名称或建议的整个鸡尾酒(例如“马提尼”或“ caipirinha”)重新用作其创作的成分。 在极少数情况下，该模型甚至会包含“ iwa kachinoki washi tango”(它想在被称为“ Jameson and Me”的詹姆森型鸡尾酒中使用)的荒谬成分。

Most importantly, these drinks may sound intriguing, but who knows if they actually taste good?

最重要的是，这些饮料听起来似乎很有趣，但是谁知道它们是否真的好吃呢？

GPT-3’s biggest limitation is that it doesn’t have any awareness of what’s correct and what isn’t. As far as I can tell, the model is just identifying patterns, rejiggering text fragments from its training data, and parroting them back to us. I’m interested to see if GPT-3 can be fine-tuned enough to be deployed where responses need to be consistently accurate, such as customer support.

GPT-3的最大局限性在于，它对正确的和不正确的不了解。 据我所知，该模型只是识别模式，从其训练数据中重新排列文本片段，然后将其重新分配给我们。 我很想知道GPT-3是否可以进行微调，以便将其部署在需要始终如一的准确响应中，例如客户支持。

For now, I think the more exciting opportunity is using AI to augment human creativity. As the saying goes, nothing is original. Innovation is essentially making new connections using our past experiences. Isn’t GPT-3 just a turbocharged version of this process?

就目前而言，我认为更令人兴奋的机会是使用AI来增强人类的创造力。 俗话说，没有什么是原创的。 创新本质上是根据我们过去的经验建立新的联系。 GPT-3是否只是此过程的涡轮增压版本？

GPT-3 ends up reminding me of a quote from the movie Limitless (stick with me here):

GPT-3结束了从电影无限 (跟紧我在这里)提醒我一个报价：

Information from the odd museum show, a half-read article, some PBS documentary — it was all bubbling up in my frontal lobes, mixing itself together into a sparkling cocktail of useful information.

奇怪的博物馆展览中的信息​​，半读的文章和一些PBS纪录片-一切都在我的额叶上冒泡，将自身融合在一起，形成有用信息的波光粼粼的鸡尾酒。

One day soon, an AI might be the co-author of your favorite drink. Until then, I’ll keep depending on the bartenders at Billy Sunday.

不久的将来，人工智能可能是您最喜欢的饮料的合著者。 在那之前，我将继续依靠Billy Sunday的调酒师。