Cognition introduces SWE-check, a fast RL-trained bug detection model for Windsurf
Original titleIntroducing SWE-Check: 10x Faster Bug Detection
AISummary
Cognition and Applied Compute RL-trained SWE-check, a specialized bug detection model for the Windsurf IDE. It matches frontier performance on in-distribution evals and is an order of magnitude faster with cheaper inference, though it trails frontier models on out-of-distribution evals (delta F1 0.29 versus 0.49 before training).
A preview is available in Windsurf Next, with a mainstream release planned.
AIWhy it matters
The post explains how production environment replication, reward linearization, and two-phase post-training trade bug-detection quality against latency for an IDE specialist model.
Source: Cognition Blog (Devin, Windsurf) · cognition.comPublished · added here