Using Jev to weigh tasks and visualize them on an Eisenhower matrix
The author built an app that uses Jev to weigh tasks and visualize them on an Eisenhower matrix, already reducing cognitive load for PMs and engineers in early testing.
Lynx open-sourced a Jev integration for the Rime input method, supporting cloud Jev models and local Jev-like models (This-That-Model, Tev 0.8b, Tev 4b). Measured latency is around 600 ms and daily cost is a few cents.
今天随手vibe了鼠须管的Jev集成,顺便进行开源。 集成了Jev云端模型能力与本地类Jev模型(This-That-Model, Tev 0.8b, Tev 4b)的支持,亲测延迟在600毫秒左右,基于语境的候选词异步且基本不会打断正常的选词体验。Jev的成本在每天几美分,完全可以接受。 欢迎测试: https://github.com/IIIIOvOIIII/RimeJev…