TypeSafe AI· @typesafeai · X·· 2026-09-22AI 评分42
AI 导读
TypeSafe 新模型 Jev 以 SQL 函数 prompt_jev() 接入 MotherDuck，文本分类速度提升约 50 倍、成本降至约 1%。10 万行数据仅需 40 秒、花费 $0.50，达到前沿 LLM 准确率，而 LLM 方案耗时 32 分钟、花费 $37。
正文 · 原文
Jev makes it easy to add natural language intelligence into the key parts of any application at scale, far cheaper and faster than has ever been possible.
50x faster.
100x cheaper.
Reliable as duck.
Text classification in MotherDuck just got ~50x faster at ~1% of the cost. prompt_jev() is a SQL function powered by Jev, TypeSafe's new system one model. 100k rows: 40s, $0.50, frontier-LLM accuracy. The LLM took 32 min and $37. Read on: https://motherduck.com/blog/motherduck-supports-jev/在 X 查看被引用的帖子
来源：TypeSafe AI · x.com