Rather than release the fully trained GPT-3.5, OpenAI used it to create several systems fine-tuned for specific tasks — each available through the OpenAI API. One — text-davinci-003 — can handle more complex instructions than models built on GPT-3, according to the lab, and is measurably better at both long-form and “high-quality” writing.
In a test on OpenAI’s Playground website, which provides a UI frontend for the models, the Pepper Content team fed several prompts to text-davinci-003 and a model based on GPT-3 (text-davinci-002). Given “What is the philosophy behind WeWork?,” the GPT-3.5-based text-davinci-003 generated this:
WeWork is a global workspace provider that believes people are the most important asset in any organization. The philosophy of WeWork is to create a collaborative environment that enables people to work together in a flexible and efficient way. The company encourages collaboration and productivity, while providing a comfortable and inspiring space.
WeWork is also committed to being a socially responsible organization, by finding ways to reduce its environmental impact, by providing meaningful work experiences, and by promoting diversity and inclusion. WeWork also strives to create meaningful experiences for its members, through its unique community-based programming, events and activities. The company believes that when people work together in an inspiring and collaborative environment, they can achieve more and create meaningful change.
It’s not perfect — note the excess commas and repetitiveness. But the copy’s certainly more engaging than what the GPT-3-based text-davinci-002 produced:
At WeWork, we believe in openness, collaboration, and community. We have reimagined what a workspace can be by bringing together a global community of creators, entrepreneurs, and startups — anyone looking to build something meaningful and transform the world. We are proud to be your neighbour, coworker, and friend.
GPT-3.5 is also better at generating blog posts, it seems. Here’s what the Pepper Content team got when they prompted text-davinci-003 to write a post about picking a sofa:
If you are looking to give your green living room a fresh look, adding the the best sofa for the space is a great way to start. However, there is more to choosing the perfect sofa than just finding a piece that looks good. You want to find a piece that is comfortable and fits your green living room décor.
In this blog, we will discuss how to pick sofa far your green living room. We will look at the different types of sofas available, the design factors to consider when making your selection, and how to choose a sofa that fits your style and budget. We will also provide tips on how to maintain and care for your new sofa. By the end of this blog, you will have all the information you need to pick the perfect for your green living room.
Again, it isn’t foolproof. GPT-3.5 oddly added the bit about a “green living room.” But also again, GPT-3 is more basic and less grammatically correct in its generation:
Sofa is one of the most basic requirements in a living room. It’s not just a piece of furniture but an important part of the décor of your living room. So, what should be the criteria while picking a sofa? If you are wondering about this then stay with me as I discuss the different aspects of the sofa would help you in picking the best one for yourself.
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
The Scale AI team even found that text-davinci-003/GPT-3.5 has a notion of meters like iambic pentameter. See:
O gentle steeds, that bear me swift and
Through fields of green and pathways so
My heart doth swell with pride to be with
As on we ride the world a-fresh to view
The wind doth whistle through our hair so
And stirs a passion deep inside of me.
My soul doth lift, my spirits soar on high,
To ride with you, my truest friend, am I
Your strength and grace, your courage and
Inspire us both to go beyond our sire.
No earthly bonds can hold us, only fate,
To gallop on, our wond’rous course create
Why did the chicken cross the road? To get to the other side.
Text-davinci-003/GPT-3.5 has cleverer responses:
Q: What did the fish say when it hit the wall? A: Dam!
Q: What did one ocean say to the other ocean? A: Nothing, they just waved.
Scale AI had the model explain Python code in the style of Eminem, a feat which text-davinci-002/GPT-3 simply couldn’t accomplish:
Yo, so I’m loopin’ through this list
With each item that I find
I’m gonna print out every letter in each one
Dog, Cat, Banana, Apple, I’m gonna get’em
all with this rhyme
So why is GPT-3.5 better than GPT-3 in these particular areas? We can’t know the exact answer without additional details from OpenAI, which aren’t forthcoming; an OpenAI spokesperson declined a request for comment. But it’s safe to assume that GPT-3.5’s training approach had something to do with it. Like InstructGPT, GPT-3.5 was trained with the help of human trainers who ranked and rated the way early versions of the model responded to prompts. This information was then fed back into the system, which tuned its answers to match the trainers’ preferences.
While anticipation builds for GPT-4, OpenAI quietly releases GPT-3.5 by Kyle Wiggers originally published on TechCrunch