Anthropic 找到 Claude 的靜默工作區把簡體中文原文的重點轉成繁體中文讀者更容易閱讀的脈絡。核心在於 Anthropic reports a small internal J-space in Claude that can carry verbalizable concepts before they appear in the final answer.
變化在哪裡
目前可核驗的事實包括：Jacobian lens method, sparse concept sets often no more than 25, explained activation variance under 10%, read-write connections up to about 100 times stronger than ordinary representations, France-to-China substitutions, and audit examples involving blackmail or score manipulation。這些細節讓新聞不只停留在發布會口號。
為什麼重要
The work suggests safety evaluation cannot rely only on final text; some relevant model states may be considered but never spoken. AI 新聞已經不能只看模型分數，還要看成本、供應、監管與真實工作流程。
接下來看什麼
The method remains approximate and token-linked, so the next question is whether it generalizes to other models and production audits. 下一步要看的不是更多宣傳，而是第三方測試、客戶續用與長時間穩定性。
參考來源：Anthropic research blog, paper Verbalizable Representations Form a Global Workspace in Language Models, Machine Heart and 36Kr、CocoLoop。