https://b.hatena.ne.jp/entry/s/www.anthropic.com/research/distillation-defenses In recent months, we’ve made substantial progress on reducing the effectiveness of distillation attacks on Claude using new methods, as we outline in this blog. Early evidence suggests that these m... https://b.hatena.ne.jp/gogatsu26/20261014#bookmark-4794359567215091298 “ポリシー　蒸留攻撃に対する防御を強化する” 2026-10-13T16:06:24Z https://b.hatena.ne.jp/naggg/20261013#bookmark-4794359567215091298 2026-10-13T09:36:18Z あとで読む https://b.hatena.ne.jp/mshkh/20261013#bookmark-4794359567215091298 これは面白いね 2026-10-13T09:31:42Z Claude AI 研究 蒸留 攻撃 セキュリティ https://b.hatena.ne.jp/toshikish/20261013#bookmark-4794359567215091298 2026-10-13T07:58:54Z https://b.hatena.ne.jp/nguyen-oi/20261013#bookmark-4794359567215091298 英語記事だけどモデル蒸留の防御策とか胸熱だな AI界隈のパクり合いはマジで仁義なき戦いだわ 2026-10-13T07:34:38Z https://b.hatena.ne.jp/tamakiii/20261013#bookmark-4794359567215091298 2026-10-13T07:14:19Z https://b.hatena.ne.jp/aku_su1/20261013#bookmark-4794359567215091298 2026-10-13T06:01:57Z https://b.hatena.ne.jp/advblog/20261013#bookmark-4794359567215091298 2026-10-13T03:33:19Z