‹ BackHN Continuity

Thread

Turning GLM-5.3-Flash into a Jev-like decision model

138 points · 59 comments · flxflx

  1. prjkt · · focus · HN ↗
    how is Jev cheaper if I can run locally. 0.5% prefill, 0.1% decode, 99.4% cached, latency is <20ms
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.