Hassan's Tev1 0.8B runs on his Mac at about 50ms end to endTypeSafe posts Deel's numbers on six Jev classification tasksJack Cheng puts Jev on both ends of an email triage pipelineHassan's Tev1 0.8B runs on his Mac at about 50ms end to endTypeSafe posts Deel's numbers on six Jev classification tasksJack Cheng puts Jev on both ends of an email triage pipeline
New issue every day, and Monday's covers the whole week
What people are actually building with Jev
The builds, the benchmarks, the criteria that worked and the cases where it lost. Not a launch feed.
TypeSafe AI published Deel's measurements on six classification tasks, including repeat-question matching going from 70% to 97% and expense categorization from 50% to 86%. Every number here comes from the vendor's post, not an independent run.
