Loading [MathJax]/extensions/tex2jax.js
Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

Devin

Devin, from Cognition Labs, is an AI software engineer with its own command line, browser, and code editor. Got your interest yet? It should. Head over to https://www.cognition-labs.com/introducing-devin and check out what they’ve built.

Image of a cyborg. Next to the cyborg are the words Cognition Labs Introducting Devin

Devin is claimed to be the world’s first fully autonomous AI software engineer. It is designed to work alongside human engineers or can work independently completing coding tasks for review. The goal is to allow engineers to focus on more interesting problems while Devin handles routine tasks.

Key capabilities of Devin include:

  • Long-term reasoning and planning to execute complex engineering tasks
  • Ability to use common developer tools like code editors, shell, browser in a sandbox
  • Real-time progress reporting and collaboration by accepting feedback
  • Learning to use new technologies by reading documentation
  • End-to-end app building, deployment and adding requested features
  • Autonomously finding and fixing bugs in codebases
  • Training and fine-tuning its own AI models
  • Contributing to open source by addressing bugs/issues on GitHub repos
  • Completing real coding jobs from platforms like Upwork

Devin was evaluated on the SWE-bench coding benchmark, correctly resolving 13.86% of open source issues end-to-end. This exceeds the previous state-of-the-art of 1.96% for complete issue resolution on this benchmark.

The examples showcase Devin’s skills in areas like steganography, web development, debugging, model fine-tuning, open source contributions across projects like sympy, Django, scikit-learn and handling real paid coding jobs.

In other words, Devin demonstrates autonomous AI capabilities for a wide range of software engineering tasks, outperforming prior models on industry benchmarks while working interactively with humans.