On Monday, OpenAI announced a new model in the GPT-3 family of large AI-powered language models, text-davinci-003, which would improve upon its predecessors by handling more complex instructions and producing longer content. Almost immediately, people discovered that it could also generate rhyming songs, limericks, and poetry on a level that GPT-3 could not produce before.
On Hacker News, commentators expressed amazement after convincing GPT-3 to write a short rhyming poem explaining Albert Einstein’s theory of relativity. Another commenter asked GPT-3 to rewrite the poem in the style of John Keats, and he obliged, dropping lines like “Mass affects the shape of time.”
Prompt: “Write a short rhyming poem explaining Einstein’s theory of general relativity in simple but precise terms”
If you want to understand Einstein’s thought
It’s not that hard if you try
General relativity is the name of the game
Where space and time can’t stay the same
Mass affects the curvature of space
Which affects the flow of the course of time
The movement of an object will be affected
By the distortion detected
The closer you are to a great mass
Slower time will seem to pass
The further you will be
Time will speed up for you to see
OpenAI makes GPT-3 available as a commercial product with an API, but for a fee ($0.02 for 1,000 tokens), anyone with an OpenAI account can experiment with AI through a special “Playground” website that does not require any coding skills.
On the Playground page, visitors can type instructions such as “write a poem about Ars Technica” or “write rhyming instructions on how to brew tea in the form of a poem”, and watch GPT-3 generate results just below the prompt.
Introduced in 2020, GPT-3 has gained fame for its ability to compose text in various styles at a human-like level, through extensive training on text fetched from the Internet and data extracted from books. It uses statistical associations between learned word positions to predict the next best word in sequence when reading from the prompt.
Of course, generating poetry with a machine is not a new hobby. As early as 1845, inventors devised ways to write expressive verse through automation. But above all, the experts Remark that the latest GPT-3 update feels like a leap forward in the complexity that comes from integrating knowledge from a wide variety of topics and styles into a template that writes consistent text.
I posted about how the image-generating AI has improved exponentially over the past month.
Well, a new text model was released for GPT-3 today.
AI can now write rhyming poems.
And explain how a candy-powered FTL drive can help me escape the otters. pic.twitter.com/vBAroN2SUv
— Ethan Mollick (@emollick) November 29, 2022
Beyond poetry, GPT-3 still has its flaws, like some have reviewed in detail. While its factual accuracy is said to have increased over time, it can still easily generate false information, limiting its applications. And GPT-3’s short-term memory is usually limited to what you’ve recently fed into a prompt. But when it comes to purely creative fictional production, GPT-3 hits pretty hard.
According to industry sources, OpenAI has quietly improved GPT-3 over time, making text-davinci-003 a notable public update. Recently, rumors about a powerful successor called GPT-4 have emerged, although OpenAI hasn’t officially announced an upcoming release.
#OpenAI #updates #GPT3 #stunning #poetry #rhyming #lyrics