跳到主内容
精选60Simon Willison 博客(RSS)模型发布/更新多源精选 ×12

Anthropic Opus 5 抗提示注入能力显著提升

Quoting Boris Cherny

原文

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 in the system card, but across PI evals and red teaming, Opus 5 is very hard to prompt inject successfully. — Boris Cherny, here's that System Card section, page 73 Tags: prompt-injection, anthropic, claude, generative-ai, ai, llms, boris-cherny

更进一步:量化金融体系

看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力

进入量化体系 →

关联讨论

同一事件的更多信源
Opus 5 发布
gabriel原文
Opus 5 在 ARC-AGI-3 得分翻四倍
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)原文
Opus 5自估41%概率为道德主体,较前代提升
AI Notkilleveryoneism Memes ⏸️原文
Anthropic 发布 Claude Opus 5,…
Anthropic Newsroom(web_list)原文
Anthropic发布Opus 5,更便宜且限制更少
TechCrunch AI(RSS)原文

相似阅读

另一事件,读法相近