jevIMAGE
MotherDuck 将上线 prompt_jev() 做 SQL 文本分类
MotherDuck 下周二直播演示 prompt_jev(),把 Jev 接进 SQL 做文本分类,10 万行 40 秒、89% 准确率、成本 0.5 美元。
MotherDuck
@motherduck2026.09.24收录原推发布于 2026.09.23

MotherDuck @motherduck原推发布于 2026.09.23
𝟭𝟬𝟬,𝟬𝟬𝟬 𝗿𝗼𝘄𝘀. 𝟰𝟬 𝘀𝗲𝗰𝗼𝗻𝗱𝘀. 𝟴𝟵% 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆. $𝟬.𝟱𝟬. Next Tuesday, we’re going live to demo our new prompt_jev() function, which brings TypeSafe AI’s Jev model to MotherDuck for fast, SQL-native text classification. Jacob Matson, Hamilton Ulmer, and Dumky de Wilde will run it against a live dataset, explain what makes Jev different from a general-purpose LLM, and unpack the benchmark September 29, 9:30am PDT Save your spot: https://luma.com/prompt_jev
x.com/motherduck/status/2102784253024989194采集于 2026.09.24 10:15