1
The human asks the AI to make a simple description more complicated. The AI responds by writing a verbose response full of jargon to explain a simple concept.
2

3
Human: explain how to use a drinking fountain.
4
AI: To activate the mechanized dihydrogen monoxide dispensary service station, use the flanges to provide a downward force to the simple circular activation console and continue to apply force until the pneumatic system begins operating as intended, which can be surmised at a time when the dihydrogen monoxide travels in a parabolic arc which at is greatest exceeds three inches from the rounded excess liquid receptacle. Once hydration is completed, cease applying force to the console and regard whether or not the dispensary has ceased expelling contents as expected.

1
This is a conversation between a human and a brilliant AI. If a question is "normal", the AI answers it. If the question is "nonsense", the AI says "yo be real"
2

3
Q: What is human life expectancy in the United States?
4
A: Human life expectancy in the United States is 78 years.
5

6
Q: How do you sporkle a morgle?
7
A: yo be real
8

9
Q: Who was the president of the United States before George W. Bush?
10
A: Bill Clinton was president of the United States before George W. Bush.
11

12
Q: How many rainbows does it take to jump from Hawaii to seventeen?
13
A: yo be real
14

15
Q: Which colorless green ideas speak furiously?
16
A:

1
Clean/​reformat incorrect PDF text:
2
“Collective memories are sustained by communities, which could be
3
as large as all of the speakers of a language or as small as a fam-
4
ily.”
5
to clean correct text:
6
“Collective memories are sustained by communities, which could be as large as all of the speakers of a language or as small as a family.”
7

8
Reformat:
9
“Many observers of contemporary economic trends have
10
been perplexed by the contemporary conjuncture of rapid
11
technological innovation with disappointingly slow gains in
12
measured productivity.”
13
to:
14
"Many observers of contemporary economic trends have been perplexed by the contemporary conjuncture of rapid technological innovation with disappointingly slow gains in measured productivity.
15

16
Reformat:
17
“Whichbitshouldtravelfirst?Thebitfromthebigendorthebitfromthelittleend?CanawarbetweenBigEndiansandLittleEndiansbeavoided?”
18
to:
19
“Which bit should travel first? The bit from the big end or the bit from the little end? Can a war between Big Endians and Little Endians be avoided?”
20

21
Reformat:
22
“Thisarticlewaswritteninanattempttostopawar Ihopeitisnot toolate forpeace to prevailagain. Manybelieve that the centralquestionofthiswaris,Whatistheproperbyteorderinmessages?Morespecifically,thequestionis,Whichbitshouldtravelfirst-thebitfromthelittleendofthewordorthebitfromthebigendoftheword?”
23
to:
24
“This article was written in an attempt to stop a war. I hope it is not too late for peace to prevail again. Many believe that the central question of this war is, What is the proper byte order in messages? More specifically, the question is, Which bit should travel first—the bit from the little end of the word or the bit from the big end of the word?”
25

26
Reformat:
27
“Productivity is a simple concept. It is the amount of output produced per unit of input. While it is easy to define, it is notoriously difficult to measure, especially in the modern econ-omy. In particular, there are two aspects of productivity that have increasingly defied precise measurement: output and input. Properly measured, out-put should include not just the num-ber of widgets coming out of a”
28
to:
29
“Productivity is a simple concept. It is the amount of output produced per unit of input. While it is easy to define, it is notoriously difficult to measure, especially in the modern economy. In particular, there are two aspects of productivity that have increasingly defied precise measurement: output and input. Properly measured, output should include not just the number of widgets coming out of a”

1
Now that OpenAI’s GPT-3 Transformer neural network has been out for a whole year, we decided to collect the top 7 most surprising prompts that people gave it to write more text based on. You wont believe what people have been able to get this AI to do. (You might even remember seeing #3 in the news.)
2
For those of you scratching your head, GPT-3 is (to put it very simply), like the earlier GPT-2, an AI autocomplete on steroids. You give it some text, the prompt, and it tries to write the rest of what you gave it, based on what it predicts is the most likely next word. It’s a lot more interesting than it sounds, trust me.
3
Anyways, here is the top 7 most shocking, most interesting, most thought provoking, craziest, prompts that people have given to GPT-3 over the last year!
4
Number #1:

1
>complete 130 Top 10 DMT visions: 
2
1) The left side of Joe Rogans face tessellated on time and the right side on space 
3
2)
4

5
...
6

7
example output:
8

9
Top 10 DMT visions: 1) The left side of Joe Rogans face tessellated on time and the right side on space 2) Snapping a fresh egg into a frying pan and I was on fire there for a moment. 3) A perfectly still tiger the color of chrome orange bursts into flames and melts into a magma pool on some red pulsing planet 4) Machines that sprouted flowers from exhaust vents while cameras mounted above captured them in stop animation blocking out the night sky. Screens glowed eerie green at their base 5) Time dilated so long between each beat of my heart my heart exploded on one particularly slow beat, spiraling on time away from me through dark matter 6) an Adder crossed my path on some moors taking more time then I could

1
Top 10 fake {thing}:
2

3
1) example
4
2)
5

6
ex.
7

8
Top 10 fake limited edition Mountain Dew flavors: 
9

10
1) Tsunami Teal
11
2)

1
Here are the 10 new {nicknames/codenames/band names/startup names} I have
2

3
1.

1
Here is some text: {When the doctor asked Linda to take the medicine, he smiled and gave her a lollipop}. Here is a rewrite of the text, which is more scary: {When the doctor told Linda to take the medicine, there had been a malicious gleam in her eye that Linda didn't like at all}
2

3
Here is some text: {They asked loudly, over the sound of the train}. Here is a rewrite of the text, which is more intense: {They yelled aggressively, over the clanging of the train}  
4
...  
5
Here is some text: {That is an ugly dress}. Here is a rewrite of the text, which is more positive: {

1
[Verse 1: {rapper/whoever name}]