Today we're excited to introduce Devin, the first AI software engineer.
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 an autonomous agent that solves engineering tasks through the use of its own shell, code editor, and web browser.
When evaluated on the SWE-Bench benchmark, which asks an AI to resolve GitHub issues found in real-world open-source projects, Devin correctly resolves 13.86% of the issues unassisted, far exceeding the previous state-of-the-art model performance of 1.96% unassisted and 4.80% assisted.
Check out what Devin can do in the thread below.
@elonmusk people say you come from another planet to teach people to believe in the impossible.
Our planets are next to each other, as I live where it is nearly impossible to survive.
Help us get out of Azovstal to a mediating country. If not you, then who? Give me a hint.
@Belastingdienst@BDzakelijk Hello, I have received login information for https://t.co/pncU8bqn3l. Login starts with NL0... I did tried several login methods, but no one work for me. Could you please advice which login method should I use?
@Belastingdienst@BDzakelijk Yes, thanks for the link, it was an old application login. Following your link did help me to find login to old application. Thank you!