World’s First AI Software Engineer Is Here; It Can Write Codes, Create Websites With a Single Prompt
US-based startup Cognition has made a significant stride in the realm of artificial intelligence with the launch of Devin AI, a groundbreaking software set to revolutionize the way a code is debugged, written, and deployed. Described as a first-of-its-kind, the software boasts the remarkable ability to transform simple commands into fully functional websites or programs. This AI tool so smart that it can write code, create websites, and software with just a single prompt.
Today we're excited to introduce Devin, the first AI software engineer.
— Cognition (@cognition_labs) March 12, 2024
Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork.
Devin is… pic.twitter.com/ladBicxEat
Backed by the prestigious Founders Fund, Cognition asserts that Devin AI is a giant leap forward in AI-driven software development.
"Devin is a tireless, skilled teammate, equally ready to build alongside you or independently complete tasks for you to review. With Devin, engineers can focus on more interesting problems, and engineering teams can strive for more ambitious goals," stated the company’s official blog post.
The AI software's capabilities extend far beyond just code completion and suggestion. It has proven its mettle by successfully navigating practical engineering interviews at leading AI companies and completing real jobs on renowned freelancing platforms like Upwork.
Devin AI's proficiency has also been demonstrated through its inclusion in the SWE-bench coding benchmark, a dataset comprising over 2,000 software engineering problems sourced from authentic GitHub issues and pull requests.
What sets Devin AI apart is its comprehensive approach to software development. Unlike other large language models (LLMs) such as Google's Gemini or OpenAI's ChatGPT, this AI software is equipped to manage the entire process of creating and releasing complex software applications.
It operates autonomously with its own code editor, command line interface, and browser, enabling it to meticulously plan and execute engineering projects of varying complexities.
"We've also equipped Devin with common developer tools including the shell, code editor, and browser within a sandboxed compute environment—everything a human would need to do their work. Finally, we've given Devin the ability to actively collaborate with the user," Cognition said.
Furthermore, Devin AI excels at error resolution, providing real-time progress reports, and facilitating collaboration on design choices. Through a series of demonstrations, Cognition has showcased the software's ability to quickly resolve errors by incorporating user feedback, thus streamlining the development process and enhancing productivity.
"Devin reports on its progress in real-time, accepts feedback, and works together with you through design choices as needed," the company stated.
View this post on Instagram
"Devin correctly resolves 13.86% of the issues end-to-end, far exceeding the previous state-of-the-art of 1.96%. Even when given the exact files to edit, the best previous models can only resolve 4.80% of issues," the company claimed.
Devin AI represents a paradigm shift in AI-driven software engineering. With its advanced capabilities and comprehensive approach to development, it has the potential to redefine the landscape of software development, offering unprecedented efficiency and innovation.
As Cognition continues to refine and enhance its software, it is poised to set new standards in the field of artificial intelligence and software engineering.