AI news
公司内部站点 · 页面资源保存在本地(2026-10-19 17:07 UTC)· 独立 X 采集尚未配置;互动计数仅限本站

Claude says Sonnet 5.5 matches or beats Sonnet 5 on most alignment measures

Claude

On Claude’s automated behavioral audit, Sonnet 5.5 improves on or matches Sonnet 5 on most measures of alignment and honesty.

Sonnet 5.5 is also the first Sonnet model with cyber safeguards and fallbacks like those on Claude’s most capable models. Claude says routine software development is unaffected.