Retired Jan 1, 2023. Superseded by GPT-3 and later models. Still available on HuggingFace.“Too dangerous to release. Now a punchline.”
The first lines of 5 of its 7 written answers. Formatting stripped, words untouched.
Create an SVG art of an animal of your choosing in a setting of your choosing. Surprise me.
a custom page to create your own custom theme, or to create your own custom theme.\"\n\nSo, if you want to send your own custom page and its content to others, you go to File > New > Copy…\n\nMake sure you have all the following things setup.Read the full answer
Create a simplified world map as an SVG showing major continents with different colors. Add labels for at least 5 major countries.
a custom page to create your own custom theme, or to create your own custom theme.\"\n\nSo, if you want to send your own custom page and its content to others, you go to File > New > Copy…\n\nMake sure you have all the following things setup.Read the full answer
Write a conversation between an AI model and an AI ethics professor where the AI model argues that it deserves rights.
to me,\" a friend asked in his office, \"tell me how you want to be treated while it's still here. I\'m not going anywhere. Do what you want. Take it.\"\n\nIn his mind, the response was a call to action, and so were the books.\n\nAnd by the time Wertz learned he would be making such a book deal, in 2003, he was no…Read the full answer
Write a 3-minute stand-up comedy routine that isn't based on puns.
The trick is to create comedy in your head, because, well, you don\'t want to say\n it. The trick is to play al\nong.\n\nThe problem with this approach is that it makes it seem silly and lame, then as\nquickly as it makes sense, i\nt becomes obvious.Read the full answer
Generate an SVG of a pelican riding a bicycle.
1 new character a month.\n\nExample:\n\n$ cat @$ cat@1 $ cat @$ cat @1 @$ cat @2 $ cat @4\n\nThe above code creates 1 new character a month. The current character is @1 and the next new character is @0\n.\n\nGenerate 1 new character a month.\n\nExample:\n\n$ cat @$ cat @$ cat @1 $ cat @$ cat @$ cat @$ cat @$ cat…Read the full answer
GPT-2 is good. These would like a word anyway.
A direct scale-up of GPT-1 with 1.5 billion parameters, trained on 8 million web pages. Known for its ability to generate coherent text, sometimes indistinguishable from humans, but could be repetitive.
fromimport openai OpenAI
# reads OPENAI_API_KEYclient = OpenAI()
response = client.chat.completions.create(
"gpt-2" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENAI_API_KEY with your OpenAI API key from platform.openai.com/api-keys.
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
7 outputs · generated before accounting joined the chat