jevPOST
Tuning the Jev threshold for recall in a family AI assistant
A builder running Jev at an arbitrary 0.8 threshold plans to tune it per product, favoring recall in a family assistant where false alarms cost latency but misses cost parental trust.
Ganesh Iyer
@ganeshiyer316Archived 8 days agoOriginally posted 2026.10.21
Ganesh Iyer @ganeshiyer316Originally posted 2026.10.21
Very good article. I am using Jev in my product with a threshold (arbitrary) of 0.8 which is mostly working fine, but this article is a good reminder to fine tune the Jev threshold to fit my product. For my family AI assistant product, I would prefer ‘recall’ over ‘precision’ as a couple of false alarms costs a minute (added latency), while a missed mistake costs a parent's trust.
This post quotes another post: x.com/hamelhusain/status/2112588257104216294
x.com/ganeshiyer316/status/2112611120544731500Archived 2026.10.21 10:03