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.
Just saw this wild Devin Demo! Truly mind-blowing. Just a glimpse of so many possibilities. Kudos to the whole Cognition team.
What are your first thoughts on Devin?
We've been using Devin to handle quick code changes and bug fixes that would otherwise take time away from our engineers. It's enabled our designers to ship prototypes and initial iterations of product changes.
Product Hunt
LangWatch Agent Simulations