推出 SWE-Check 模型:10 倍速 Bug 檢測
Introducing SWE-Check: 10x Faster Bug Detection2026.04.14Smaller specialized models can match or beat frontier generalists on the tasks they're trained for. Working with Applied Compute, we RL-trained SWE-check, a bug detection model that matches Opus 4.6 on our internal evals while running ~10x faster.
重點導讀
**SWE‑Check 是 Cognition 與 Applied Compute 合作研發的專門化 bug 檢測模型,能以約 10 倍速度比 Opus 4.6 同等效能。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
信源出處cognition.ai
Introducing SWE-Check: 10x Faster Bug Detection2026.04.14Smaller specialized models can match or beat frontier generalists on the tasks they're trained for. Working with Applied Compute, we RL-trained SWE-check, a bug detection model that matches Opus 4.6 on our internal evals while running ~10x faster.
本文為 888news 精選之重點導讀。若需閱讀作者完整原文、技術細節與官方討論,請前往原始網站。
來源: Cognition / Devin Blog (cognition.ai)
開啟原文