open ai gpt

為什么大肆宣傳？ (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?”

幾周前，OpenAI發(fā)布了GPT-3，這是他們語言生成模型的最新版本。 從編寫小說到生成有效JavaScript的所有過程中，GPT-3的例子Swift傳播開來，并引起了廣泛的新聞報(bào)道，標(biāo)題為“什么是GPT-3，我們應(yīng)該害怕嗎？”

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

紐約時(shí)報(bào)的Farhad Manjoo 這樣說 ：

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.

我從來沒有真正擔(dān)心過計(jì)算機(jī)會(huì)接任我的工作，因?yàn)樗坪跤肋h(yuǎn)不可能實(shí)現(xiàn)。 并非經(jīng)常，我的手機(jī)認(rèn)為我要寫“ ducking”一詞。 用電腦寫報(bào)紙專欄嗎？ 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，這一天快到了。 本月，位于舊金山的人工智能研究實(shí)驗(yàn)室OpenAI開始允許有限地訪問一件既令人驚奇，詭異，令人毛骨悚然的軟件，又不至于有點(diǎn)恐怖的軟件。

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？ 該模型是在大量文本上進(jìn)行訓(xùn)練的-根據(jù)The Verge的說法，英語維基百科的全部?jī)H占總數(shù)據(jù)集的0.6％ -并使用1,750億個(gè)參數(shù)進(jìn)行了微調(diào)。 與其他學(xué)習(xí)者不同，GPT-3無需進(jìn)行過多的培訓(xùn)就可以針對(duì)各種專業(yè)任務(wù)產(chǎn)生相當(dāng)不錯(cuò)的輸出。

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，只能通過私有Beta訪問GPT-3的API。 我最近收到了邀請(qǐng)，迫不及待地要接受測(cè)試。 特別是，我很好奇該模型將如何處理既需要專業(yè)知識(shí)又需要?jiǎng)?chuàng)造力的任務(wù)，特別是在我至少能判斷其答案質(zhì)量的領(lǐng)域。

GPT-3的混合學(xué) (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:

要開始使用GPT-3，我從芝加哥機(jī)構(gòu)Billy Sunday和我一直以來最喜歡的雞尾酒吧中舉了一些例子對(duì)它進(jìn)行了培訓(xùn)。 我為模型提供了一些上下文，并列出了一些真正的比利周日雞尾酒的主要成分，名稱和配方：

Here are some high-end drinks on the menu at Billy Sunday, a Chicago cocktail bar.Ingredient: rum
Cocktail: TROPIC THUNDER — RUM BLEND, UBE ORGEAT, COCONUT, ORANGE & LIMEIngredient: tequila
Cocktail: PARCHA PUNCH — REPOSADO TEQUILA, MEZCAL, PASSION FRUIT, OREGANO, LIME & SALTIngredient: gin
Cocktail: 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:

在將Billy Sunday菜單上的所有7種時(shí)令雞尾酒都加入API后，我提示它添加了更多成分，以查看會(huì)產(chǎn)生什么效果。 GPT-3的輸出以粗體顯示 ：

Ingredient: mezcalCocktail: EL DIABLO — MEZCAL, CINNAMON, LEMON, ORANGE, ANCHO CHILI & SALTIngredient: fernet branca
Cocktail: THE BERLINER - FERNET BRANCA, GINGER, LEMON, SODA & GINGER ALEIngredient: macallan
Cocktail: 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 chartreuse
Cocktail: THE GREEN EYESHADE - GREEN CHARTREUSE, BOURBON, LEMON, ORANGE & SAGEIngredient: bacon-infused bourbon
Cocktail: 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.

它的建議并不完美-例如， 柏林人已經(jīng)是杜松子酒和苦艾酒的知名雞尾酒了-但總體而言，這些飲料不會(huì)在任何時(shí)尚雞尾酒吧的菜單上讓您感到不適。

Kicking it up a notch

踢一個(gè)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包含一個(gè)名為temperature的整潔參數(shù)，該參數(shù)介于0和1之間，用于控制輸出的隨機(jī)性。 OpenAI將其比喻為調(diào)整創(chuàng)造力。 上面的示例是在0.1的極低溫度下生成的。

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):

當(dāng)我將溫度設(shè)置為0.1并提示GPT-3使用水果利口酒Pimm's制作雞尾酒時(shí)，它做出了可以預(yù)測(cè)的選擇，并且?guī)缀踅ㄗh使用標(biāo)準(zhǔn)的Pimm's Cup (盡管正確的配料是姜汁啤酒，而不是姜汁)：

Ingredient: pimm's
Cocktail: 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:

在我將溫度調(diào)到0.5之后，GPT-3決定在經(jīng)典雞尾酒上加些捻：

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

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

在溫度為0.9的情況下，GPT-3真正發(fā)揮了創(chuàng)意：

Ingredient: pimm’s
Cocktail: 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:

這是GPT-3在溫度升高到0.9時(shí)發(fā)明的一些有趣的食譜：

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能夠輕松生成合理的文本確實(shí)令人印象深刻，但它不會(huì)很快占領(lǐng)整個(gè)世界。 我挑選了上面最有趣的示例，但是該模型犯了很多明顯的錯(cuò)誤。 例如，它有時(shí)將流行飲料的名稱或建議的整個(gè)雞尾酒(例如“馬提尼”或“ caipirinha”)重新用作其創(chuàng)作的成分。 在極少數(shù)情況下，該模型甚至?xí)?iwa kachinoki washi tango”(它想在被稱為“ Jameson and Me”的詹姆森型雞尾酒中使用)的荒謬成分。

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

最重要的是，這些飲料聽起來似乎很有趣，但是誰知道它們是否真的好吃呢？

Billy Sunday.)Billy Sunday 。)

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，它對(duì)正確的和不正確的不了解。 據(jù)我所知，該模型只是識(shí)別模式，從其訓(xùn)練數(shù)據(jù)中重新排列文本片段，然后將其重新分配給我們。 我很想知道GPT-3是否可以進(jìn)行微調(diào)，以便將其部署在需要始終如一的準(zhǔn)確響應(yīng)中，例如客戶支持。

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，我認(rèn)為更令人興奮的機(jī)會(huì)是使用AI來增強(qiáng)人類的創(chuàng)造力。 俗話說，沒有什么是原創(chuàng)的。 創(chuàng)新本質(zhì)上是根據(jù)我們過去的經(jīng)驗(yàn)建立新的聯(lián)系。 GPT-3是否只是此過程的渦輪增壓版本？

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

GPT-3結(jié)束了從電影無限 (跟緊我在這里)提醒我一個(gè)報(bào)價(jià)：

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.

奇怪的博物館展覽中的信息??，半讀的文章和一些PBS紀(jì)錄片-一切都在我的額葉上冒泡，將自身融合在一起，形成有用信息的波光粼粼的雞尾酒。

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.

不久的將來，人工智能可能是您最喜歡的飲料的合著者。 在那之前，我將繼續(xù)依靠Billy Sunday的調(diào)酒師。

翻譯自: https://medium.com/swlh/gpt-3-invented-cocktails-you-might-actually-want-to-try-e42783a58195

open ai gpt

總結(jié)

以上是生活随笔為你收集整理的open ai gpt_您实际上想尝试的GPT-3 AI发明鸡尾酒的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。