Ars Technica
On Monday, OpenAI announced a new model in the GPT-3 family of AI-powered large language models, text-davinci-003, that reportedly improves on its predecessors by processing more complex instructions and producing longer content. Almost immediately, folks discovers that it could also generate rhyming songs, limericks and poetry at a level that GPT-3 was previously unable to produce.
On Hacker News, commentators expressed surprise 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 it obliged by lines like “Mass affects the shape of time.”
Prompt: “Write a short rhyming poem explaining Einstein’s general theory of relativity in simple but precise terms”
If you want to understand Einstein’s thought
It’s not that hard if you give it a chance
General relativity is the name of the game
Where space and time cannot stay the same
Mass affects the curvature of space
Which affects the course of the race of time
The movement of an object is affected
By the deformation that is detected
The closer you are to a large mass
The slower time seems to pass
The further you may 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 per 1,000 tokens), anyone with an OpenAI account can experiment with the AI through a dedicated “Playground” website that requires no coding skill is.
On the Playground page, visitors can type instructions such as “write a poem about Ars Technica” or “write rhyming instructions about making tea in the form of a poem”, and watch GPT-3 generate results just below the prompt.
-
GPT-3 writes a poem about Ars Technica, using information GPT-3 already knows about the site.
Ars Technica
-
GPT-3 writes a rhyming poem about making tea, combining instructions for making tea into rhyming verses.
Ars Technica
-
GPT-3 writes a convincing limerick about Benj Edwards as AI.
Ars Technica
Introduced in 2020, GPT-3 gained notoriety for its ability to compose text in different styles at a similar level to a human, thanks to extensive training on text scraped from the Internet and data from books. It uses statistical associations between learned word positions to predict the next best word in the sequence while reading the prompt.
Generating poetry with a machine is of course not a new pastime. As far back as 1845, inventors have devised ways to write expressive verse through automation. But mostly experts Remark that GPT-3’s latest update feels like a step forward in complexity that comes from integrating knowledge across a wide variety of topics and styles into one model that writes coherent text.
I’ve posted about how image-generating AI has gotten exponentially better over the past month.
Well, a new text model was released today for GPT-3.
AI can now write rhyming poems.
And acrostics.
And limericks.
And explain how a candy-powered FTL drive could help me escape otters. pic.twitter.com/vBAroN2SUv— Ethan Mollick (@emollick) November 29, 2022
In addition to poetry, GPT-3 still has its flaws, such as some have researched in detail. While its factual accuracy has reportedly increased over time, it can still easily generate false information, limiting its applications. And GPT-3’s short-term memory is generally limited to what you recently entered it within a prompt. But when it comes to purely creative fictional output, GPT-3 shoots pretty well.
According to industry sources, OpenAI has quietly improved GPT-3 over time, making text-davinci-003 a notable public upgrade. Rumors have recently surfaced about a powerful successor called GPT-4, although OpenAI has not officially announced an upcoming release.
