WHAT NEW IN X10.30 FRI

X 上的 AI 合集档案 · 22 个合集 · 61,986 条

jevVIDEO

Jev 1.14 图像定位 demo:找出热狗并画框

用 Jev 1.14 的图像支持做「Where is Hotdog」小 demo,说出图中物体即返回带耗时和成本的边界框。

Trevin Chow
@trevin13 天前收录原推发布于 2026.10.16
Trevin Chow @trevin原推发布于 2026.10.16
在 X 上打开原推

Built a small demo of @typesafeai Jev 1.14 which adds image support: Where is Hotdog? 🌭 Name something in the picture and Jev tries to find it, drawing a bounding box around the match. Every search shows how long it took and what it cost. When image checks are this fast and cheap, you can start putting them into interactions and workflows where you wouldn’t have justified the cost before. Try it: https://demos.trev.in/hotdog

这条是引用着另一条写的:x.com/typesafeai/status/2110536685805355064

x.com/trevin/status/2111119504826859956采集于 2026.10.17 10:05