GPT-3 is Now Updated! This AI language model generates rhyming compositions in various styles

GPT-3 is Now Updated! OpenAI announced a new model in the GPT-3 family of AI-powered large language models, text-DaVinci-003, which it claims improves on its predecessors by handling more complex instructions and producing content in longer forms. According to ARS Technica, OpenAI upgrades GPT-3, and almost immediately folks discovered that it could also produce rhyming songs, limericks, and poetry at a level that GPT-3 could not previously 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 complied, dropping lines like "Mass affects the shape of time."

Prompt: "Write a short rhyming poem explaining Einstein's theory of general relativity in easy but accurate terms"

"If you want to understand Einstein's thought

It's not that hard if you give it a shot

General Relativity is the name of the game

Where space and time cannot remain the same

Mass affects the curvature of space

Which affects the flow of time's race

An object's motion will be affected

By the distortion that is detected

The closer you are to a large mass

The slower time will seem to pass

The farther away you may be

Time will speed up for you to see"

OpenAI upgrades GPT-3 and makes it 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 special "Playground" website that requires no coding skill.

On the Playground page, visitors can type instructions such as "write a poem about Ars Technica" or "write rhyming instructions about how to brew tea in the form of a poem," and watch GPT-3 generate results just below the prompt.

Unlike most AI systems which are designed for one use-case, the API today provides a general-purpose "text in, text out" interface, allowing users to try it on virtually any English language task. You can now request access in order to integrate the API into your product, develop an entirely new application.

Given any text prompt, the API will return a text completion, attempting to match the pattern you gave it. You can "program" it by showing it just a few examples of what you'd like it to do; its success generally varies depending on how complex the task is. The API also allows you to hone performance on specific tasks by training on a dataset (small or large) of examples you provide, or by learning from human feedback provided by users or labelers.

OpenAI has designed the API to be both simple for anyone to use but also flexible enough to make machine learning teams more productive. In fact, many of OpenAI's teams are now using the API so that they can focus on machine learning research rather than distributed system problems. Today the API runs models with weights from the GPT-3 family with many speed and throughput improvements.

ChatGPT

The San Francisco-based company has released a demo of a new model called ChatGPT, a spin-off of GPT-3 that is geared toward answering questions via back-and-forth dialogue. In a blog post, OpenAI says that this conversational format allows ChatGPT "to answer follow-up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests."

In particular, ChatGPT—like Galactica, Meta's large language model for science, which the company took offline earlier this month after just three days—still makes stuff up. There's a lot more to do, says John Shulman, a scientist at OpenAI: "We've made some progress on that problem, but it's far from solved."