avatarUgur Akinci

Free AI web copilot to create summaries, insights and extended knowledge, download it at here

4690

Abstract

0/1*jFax3XhfV9mam-k4kI_NSQ.png"><figcaption>A paragraph is summarized into one sentence</figcaption></figure><p id="2e04">Another use of text summarization is to present a user with a auto summarized dialog, with a <i>read more </i>option, which can then expand into the longer un-summarized version.</p><figure id="82f1"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="58c0">Keywords</h2><p id="4f31">Keywords can be extracted from a block of text. You can configure the environment to be conservative and select only keywords from the text. Or a higher <i>temperature </i>can be set to where related words or keywords are generated.</p><figure id="286e"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*FGE3OBMcMyDDcpgKRQb9AQ.png"><figcaption>Key words generated from a Wikipedia paragraph.</figcaption></figure><p id="3a5c">This is very helpful to categorize text and create a search index. In the image above a extract on soccer was taken from Wikipedia. GPT-3 converted this quite large paragraph into six key words or themes.</p><figure id="93e7"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="e562">Parse Unstructured Data</h2><p id="3191">Create tables from long form text by specifying a structure and supplying some examples.</p><figure id="6942"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*X9YWrg_wlpg3hbKCmoq62A.png"><figcaption></figcaption></figure><p id="6984">Here you can see the first entry is directly related to the sentence. The subsequent entries are somehow related and still relevant and applicable.</p><figure id="90e7"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="7585">Classification</h2><p id="72fe">Classify items into categories via example inputs. Companies are named with categories defined. A new company can be mentioned and auto classified.</p><figure id="2265"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*IOkqXlAV2ZCxFpMNaeL2XA.png"><figcaption>With limited training data a new company can be mentioned and auto classified.</figcaption></figure><figure id="9feb"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="281c">Extract Contact Information</h2><p id="0f31">Extract contact information from a block of text. In this case, an address.</p><figure id="8a87"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*5imfXfm2gvrGbA1uRTOkiQ.png"><figcaption>A complete address from the free text message.</figcaption></figure><figure id="ea15"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="95b2">Summarize For A Second Grader</h2><p id="9a5d">This functionality takes a complex and relatively long piece, summarize and simplifies it into a sentence or two.</p><figure id="0da8"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*ReUEmdf0XZ3r54rcYqibfA.png"><figcaption>A large and complex piece of text is summarized and simplified.</figcaption></figure><figure id="d85e"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h1 id="e7ec">Conclusion</h1><p id="3c79">There are definitely good implementation opportunities for the Conversational AI aspect of GPT-3.</p><figure id="6f46"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*5m48Qw7hRcbi7gsL5ZoRAQ.png"><figcaption>Restaurant review is created from a few key words and the restaurant name.</figcaption></figure><p id="2f01">As a support API where text can be processed to assist existing NLU functionality, there is a very real use case.</p><p id="25d7">As mentioned, GPT-3 can be a great help in pre-processing user input as a help for the NLU engine. The challenge is that GPT-3 seems very well positioned to write reviews, compile questions and have a general conversation. This could lead to a proliferation of bots writing reviews, online adds and general copywriting tasks.</p><figure id="b3c1"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*26A6H7nHUvLW10CkKSlaCQ.png"><figcaption>An apple pie review based on four generic words.</figcaption></figure><p id="4fae">This automation does not need to be malicious in principle. Open AI is seemingly making every effort to ensure the responsible use of the API’s.</p><p id="99a2">The fact the extensive

Options

training is not required, and a few key words or phrases can <i>point </i>the API in the right direction, is astounding.</p><p id="a28c">There are however opensource alternatives for most of the functionality available.</p><figure id="04a8"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="3cbc">Positives</h2><ul><li>GPT-3 has quite a bit of functionality which can serve to augment a current chatbot.</li><li>Dialog can be diversified with the NLG capability.</li><li>General chit-chat can easily be created.</li><li>Copywriting is made easy for slogans, headlines, reviews etc.</li><li>Text transformation</li><li>Text generation</li><li>Creating a general purpose bot to chat to.</li><li>With their underlying processing power and data, creating flexible Machine Learning stories should be a good fit.</li></ul><figure id="a4fc"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><h2 id="b03c">Not-so Positives</h2><ul><li>The API is cloud hosted</li><li>Cost</li><li>Social media bot content generation</li><li>Not a framework for sustainable chatbot scaling; <i>yet</i>.</li><li>Possible over and under steering with training data.</li></ul><figure id="bfc0"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure><div id="9145" class="link-block"> <a href="https://cobusgreyling.me/thank-you-for-subscribing/"> <div> <div> <h2>Subscribe to my newsletter.</h2> <div><h3>NLP/NLU, Chatbots, Voice, Conversational UI/UX, CX Designer, Developer, Ubiquitous User Interfaces, Ambient…</h3></div> <div><p>cobusgreyling.me</p></div> </div> <div> <div style="background-image: url(https://miro.readmedium.com/v2/resize:fit:320/0*sxVx6IgC_6AZXIX-)"></div> </div> </div> </a> </div><div id="1141" class="link-block"> <a href="https://cobusgreyling.medium.com"> <div> <div> <h2>Cobus Greyling - Medium</h2> <div><h3>Read writing from Cobus Greyling on Medium. NLP/NLU, Chatbots, Voice, Conversational UI/UX, CX Designer, Developer…</h3></div> <div><p>cobusgreyling.medium.com</p></div> </div> <div> <div style="background-image: url(https://miro.readmedium.com/v2/resize:fit:320/0*e6KH9V073Egac4ua)"></div> </div> </div> </a> </div><div id="2e0e" class="link-block"> <a href="https://cobusgreyling.medium.com/gpt-3-conversational-ai-chatbots-3fb1cfb99942"> <div> <div> <h2>GPT-3: Conversational AI & Chatbots</h2> <div><h3>What Will The Impact Be On Chatbot Design & Development</h3></div> <div><p>cobusgreyling.medium.com</p></div> </div> <div> <div style="background-image: url(https://miro.readmedium.com/v2/resize:fit:320/1*VKDfysUcdNJtCEQwmxSE-w.jpeg)"></div> </div> </div> </a> </div><div id="59bc" class="link-block"> <a href="https://openai.com/"> <div> <div> <h2>OpenAI</h2> <div><h3>OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits…</h3></div> <div><p>openai.com</p></div> </div> <div> <div style="background-image: url(https://miro.readmedium.com/v2/resize:fit:320/0*SzqTQqBlnX8UOa8A)"></div> </div> </div> </a> </div><div id="47a1" class="link-block"> <a href="https://openai.com/blog/openai-api/"> <div> <div> <h2>OpenAI API</h2> <div><h3>We're releasing an API for accessing new AI models developed by OpenAI. Unlike most AI systems which are designed for…</h3></div> <div><p>openai.com</p></div> </div> <div> <div style="background-image: url(https://miro.readmedium.com/v2/resize:fit:320/0*iD7cRdNC9EDQkZQ2)"></div> </div> </div> </a> </div><figure id="f7c7"><img src="https://cdn-images-1.readmedium.com/v2/resize:fit:800/1*mlG74R9ZBY7NQcvQ2C8dMw.png"><figcaption></figcaption></figure></article></body>

HUMOR | INVESTIGATIVE NONSENSE | TRUTHFUL HYPERBOLE

The Tragedy of a Billionaire Who Collected Winds

Watch for want you want lest you get it

Photo by Nita: https://www.pexels.com/photo/white-dandelion-flower-shallow-focus-photography-54300/

We’ll call him PX to protect his anonymity.

He was the richest man in the world, due to an accidental early investment in the stocks of Microsoft, IBM, Oracle, Apple, and Amazon.

Yet, preliminaries first.

What is Wealth?

When you can’t tell how much money you’ve got, that’s wealth.

When IRS sends a limousine to pick up your income tax return by a white-gloved chauffeur, that’s wealth.

It’s the greatest feeling in the world until you discover that your confidential accountant made more than you did last year and owns half of the Caribbean.

What’s Wind?

Depends.

It varies from an embarrassing conversation breaker at the Thanksgiving table to the cataclysm that sank Atlantis.

But enough of science talk. Let’s go back to our Breaking News.

Existential Mania

PX did what all rich folks do: he started to collect stuff.

Money in the bank was not enough to make him happy anymore.

Having the most incredible collection in the world became an existential obsession with him. People who had a look at his collection should have a brain aneurism of jealousy and envy, was what he wanted.

He bought yachts as long as football fields, so many of them that he had to build the world’s largest marina off the coast of California. But soon every Arab sheik, Russian oligarch, and Instagram influencer also started to parade enormous yachts, some mistaken for aircraft carriers.

He married every beautiful woman he set his eyes on. But Ottoman sultans in the past had hundreds of Circassian beauties in their harems without owning a single Amazon stock. Linda Wolfe made it to the Guinnes Book of World Records by marrying 23 times. No big deal.

PX started to collect Lamborghinis. But every other 18-year old affiliate marketer started to post selfies online, leaning against a yellow Lambo with a juvenile sneer. That didn’t cut it either.

Never Before

Thus he decided to collect something that has never been collected before in human history: The wind.

A great idea that would cement his reputation as the world’s richest top dog for generations to come.

But how?

Proliferation of generous research funds offered to M.I.T and CalTech for wind research at this same period is no coincidence. The benefactor read “International Aerial Displacement Research Foundation” on the paperwork but the insiders knew that PX was the real donor pulling the strings from behind the scenes.

Enter EQR

After a couple of billion dollars of research money and two years of 24–7 academic pain in the butt, PX got the good news he was waiting for: EQR, that is, Electromagnetic Quantum Resonance, was a success!

With EQR, you could scan all weather events into an N-dimensional quantum matrix and then create the same wind by collapsing its wave-function at will, by using a special EQR Hydron Projector custom-built exclusively for PX.

The Beginning

Armed with the amazing EQR technology, PX started to collect local winds.

He visited Patagonia, for example, and captured the matrix of rare snow storms.

Then he proceeded to send his employees across the globe to capture mountain breezes from Himalayas, mistrals from the Alps, Santa Ana from California, Chinook from Canada, Khamsin from Egypt, Lodos and Poyraz from Turkey.

Pretty soon he was gloating that he owned the only wind collection in the world, blowing a storm of envy through the locker rooms of members-only country clubs across the nation.

The Middle

But what’s an expensive collection if you don’t or can’t flaunt it?

Soon the word got out and found its way to all the major news networks.

In a 60 Minute Special interview, PX did not hide his contempt for the Japanese firm that bought Van Gogh’s sunflowers for $90 million, only to lock it up in a bank vault.

“Great collections belong to humanity,” he opined, looking straight into the camera. “We the business elite who are fortunate enough to put together such amazing collections should not deprive the public from the pleasure of enjoying the rare fruits of our worldly success.” He almost passed his own wind while finishing that sentence.

Soon exposition and performance requests started to pour in.

The genie was out of the bottle and it was too late to screw it back in.

Photo by Pixabay: https://www.pexels.com/photo/earth-planet-76969/

The End

PX started to host PR events and charity fundraisers by creating small Oklahoma twisters at football stadiums, followed by other “aerial displacement” shows that his staff could control easily with the EQR hydron projector.

But his detractors and business rivals were relentless. They raised the ugly possibility that all that was a show and a sham. He was accused of timing the EQR events to match the dates of naturally occurring storms.

The allegation was all over the Internet, soon accepted as the shocking travesty of a shameless self-promoter.

But PX was not a man to shy away from a challenge. His integrity was on the line.

He couldn’t afford to lose his reputation as the world’s most powerful man to fake news masquerading as truth.

So he planned a major spectacle to put an end to all scurrilous rumors for good in the heart of the Sahara Desert which he owned at that point.

The day of the Great Event arrived.

PX, his top 100 scientists, and a gaggle of hand-picked media celebrities took their seats behind the control center protected by bullet-and-radiation-proof glass. The air was thick with the excitement and fear of the unknown. You’d think they were in Los Alamos back in 1945, waiting for the test detonation of the world’s first nuclear bomb.

The goal was to create-on-demand the last ten Atlantic storms simultaneously to leave no doubt as to the authenticity of this amazing collection.

PX pushed the red button with the confidence of a Julius Caesar crossing the Rubicon and kicked the mighty EQR Hydron Projector to life.

First there was a light buzz. It developed into a sweet breeze that was most welcomed in the 115 F weather.

The breeze soon picked up speed and built strength to a sand storm.

As the EQR hydron projector started to groan and shake, the sand storm built into ten different hurricanes that crossed the borders of six neighboring nations.

Within ten minutes a monstrous cyclone, the kind seen once in every hundred years over the Pacific Ocean, pulverized the Sahara Desert, blowing to smithereens everything on its path, creating a hole two hundred miles across and thirty miles deep.

Two of the scientists were found wrapped around a lamb post in Beijing, China, a month later.

Five members of BBC’s TV crew woke up on a glacier in Greenland, shivering and not remembering how they got there.

The famous red button washed ashore on a beach in Hawaii and sold on eBay immediately for an obscene amount of money.

And the ugly hole left behind, repositioned by a Madison Avenue marketing agency as the Grand Canyon of Africa, is today a tourist attraction visited by millions of sweltering tourists each year, helping six nations balance their annuals budgets.

Five years after the disaster, there is no word from Mr. PX. No one knows his whereabouts. All efforts to find him have failed.

That’s the bad news.

The good news is, he’s still to this day the richest missing person ever recorded in world history.

Humor
Satire
Wealth
Rich
Funny
Recommended from ReadMedium