精选理由
Anthropic发了新发现：删掉Claude的J-space后它说话正常但推理变弱，想了解模型内部机制可以看看。
Anthropic在推文中披露，移除Claude的J-space（内部表征空间）后，模型仍能流畅表达、回忆事实和完成文本分类，但在多步推理任务上显著变差。该发现类比人类认知中的深思熟虑与自动过程。J-space的缺失不影响基础语言能力，却损害了需要连贯逻辑链的复杂推理。这一实验揭示了Claude内部机制与推理能力的关键关联。
原文 · Anthropic
For most things, Claude actually doesn’t need its J-space. If we delete the J-space, Claude still sp...
For most things, Claude actually doesn’t need its J-space. If we delete the J-space, Claude still speaks fluently, recalls facts, and classifies text—but becomes bad at some tasks like multi-step reasoning. It’s similar to deliberate vs. automatic processing in human cognition. 💬 5 🔄 31 ❤️ 570 👀 65763 📊 68 ⚡