TypeSafe AI · @typesafeai · X·2026-09-22 09:21·2小时前
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。

TypeSafe AI@typesafeai
42AI 编辑部评分,满分 100
2026-09-22 09:21· 2小时前
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。

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.

MotherDuckText 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 ...