精选理由
Anthropic 新出的 Sonnet 5 能自己检查结果，做复杂任务还便宜，挺靠谱的。
Anthropic 推出 Claude Sonnet 5，早期合作伙伴发现它能完成之前 Sonnet 系列中断的复杂任务。该模型无需提示即可自动检查自身输出。它还能以有吸引力的价格执行完整的智能体工作。
原文 · Claude
Early access partners found Sonnet 5 finishes complex tasks where previous Sonnets stopped short, ch...
Early access partners found Sonnet 5 finishes complex tasks where previous Sonnets stopped short, checks its own output without being asked, and does all its agentic work at an attractive price point. 💬 32 🔄 40 ❤️ 1897 👀 225963 📊 171 ⚡