X：Cognition (@cognition)· @cognition·· 6 天前AI 评分
Devin 成本效率最高提升 40%，Fusion 与 Normal 模式降价 30-40%
R to @cognition: Model independence lets us call the best model for each part of Devin’s work. We continue refining the harness around them by batching more work per call, running more actions in parallel, and making the most of cached context. Read how the latest models and harness improvements deliver better price-performance: https://devin.ai/blog/more-efficient-devin
Cognition 宣布 Devin 成本效率最高提升 40%，Fusion 和 Normal 模式便宜 30-40%，Ultra 模式便宜 15-20%，Devin Review 最高便宜 70%，原因是采用了最新模型和更高效的 harness。
来源：X：Cognition (@cognition) · x.lingyaoai.com