Wednesday, March 27, 2024

Devin: AI software engineer? + OpenDevin; SWE-bench

 Introducing Devin, the first AI software engineer

With our advances in long-term reasoning and planning, Devin can plan and execute complex engineering tasks requiring thousands of decisions. Devin can recall relevant context at every step, learn over time, and fix mistakes.

SWE-bench
Can Language Models Resolve Real-World GitHub Issues?

"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."



a sceptic view on this



OpenDevin, an open-source project aiming to replicate Devin, an autonomous AI software engineer who is capable of executing complex engineering tasks and collaborating actively with users on software development projects. This project aspires to replicate, enhance, and innovate upon Devin through the power of the open-source community.



  • AI startup Cognition develops an AI software engineering platform that can automate entire projects.
  • Devin has impressed big names in AI, like former Tesla AI director Andrej Karpathy.
  • Well-funded by Peter Thiel and tech leaders, Cognition plans to offer early access to Devin for engineering teams soon.


No comments: