1
Quoting Boris Cherny
Opus 5在防提示注入上表现惊人,成为最安全的大模型之一。
More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried…
Opus 5在防提示注入上表现惊人,成为最安全的大模型之一。
More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried…
标题提示AI采用步骤,但当前链接无法访问,建议关注相关主题的后续内容
Article URL: https://claude.ai/code/artifact/bfdfaef9-bc62-4dfe-ba9e-c58a26c9accf Comments URL: https://news.ycombinator.com/item?id=48942554 Points: …
AI 应用模式新视角,Boris Cherny 拆解常见 AI 原型,帮你快速理解不同交互逻辑。
Article URL: https://twitter.com/bcherny/status/2071379474277613732 Comments URL: https://news.ycombinator.com/item?id=48723732 Points: 1 # Comments: …