英伟达研究：AI 支架比模型本身更关键
原标题：Nvidia just showed that the harness, not the AI model, is now the real hero
AI 摘要
英伟达发布新研究，表明在长时程任务中，AI 的“支架”（harness）比底层模型更重要。通过定制支架并引入“监督者”组件，英伟达让 Claude Opus 5 在 ARC-AGI-3 基准上达到 100% 得分，而无支架时仅 30%。该研究强调开放支架系统对用户控制和安全性的重要性，并呼应了 OpenAI 和 Databricks 的相关发现。
正文节选
Nvidia published some interesting new research on Friday suggesting it’s the harness, more than the underlying model, that is far more important when asking an AI to do long-horizon tasks. The tldr: simply by using a custom harness tweaked to handled memory well and including a “supervisor” boss-like component, researchers got Claude Opus 5 to achieve a 100% score on the interactive reasoning benchmark ARC-AGI-3. (That’s a benchmark that has particularly irked rival frontier lab OpenAI.) Without