Ever since its release last month, OpenAI’s GPT-3 has been in the news for a variety of reasons. From being the largest language model ever trained to outranking state of the art models on tasks such as translation and question-answering, GPT-3 has set new benchmarks for natural language processing.
Now, in the latest news, Sharif Shameem, the founder of debuild.co, a startup which enables developers to build apps with minimum effort, has leveraged GPT-3 to generate code!
This is mind blowing.
— Sharif Shameem (@sharifshameem) July 13, 2020
With GPT-3, I built a layout generator where you just describe any layout you want, and it generates the JSX code for you.
W H A T pic.twitter.com/w8JkrZO4lk
All Shareen had to do was to enter the text that captures the essence of the product and the generator dishes out code.
According to Shareen, he only had to write 2 samples to give GPT-3 context for what he wanted to do. It then properly formatted all of the other samples.
“There were a few exceptions, like the JSX code for tables being larger than the 512 token limit. If I wanted it to write output plain HTML/CSS instead of JSX, all I would have to do would be to re-write my 2 initial samples in HTML/CSS. Then all of GPT-3’s outputs would be in plain HTML/CSS,” added Shareen.
Here are other instances where GPT-3 made coding more fun and app development easy:
Building a to-do list app:
I built a todo list app simply by describing it to GPT-3.
— Sharif Shameem (@sharifshameem) July 18, 2020
It generated the React code for a fully functioning app within seconds.
I'm becoming more impressed and aware of its capabilities every single day. pic.twitter.com/QGrClar03s
Generating code for Google homepage
Here's a sentence describing what Google's home page should look and here's GPT-3 generating the code for it nearly perfectly. pic.twitter.com/m49hoKiEpR
— Sharif Shameem (@sharifshameem) July 15, 2020
OpenAI with the beta release of its API has attracted a plethora of experts and amateur developers to implement exotic machine learning models for their software development chores. Now it will be only a matter of time before more innovations surface in the developers community!