AI & ML
Teaching Sidekick to say no: automated data curation with LLM judge consensus
Shopify Engineering0 views
Production training data only captures successful queries; it can't teach a model when to say no. We built an automated curation pipeline using LLM judge consensus to close that gap.
Source:https://shopify.engineering/sidekick-curationPreviousClustering billions of products for agentic commerce with Catalog APINextQuick: An internal hosting platform for the AI era
Related posts
We deleted our old reminder CronJob from Git and Argo CD kept running it for six weeks
0dev.to
Port-forwarding to a model on a private GKE GPU cluster: DNS endpoint or Connect gateway
0dev.to
You Were Sure You Knew How the Release Pipeline Worked Until You Wrote It Down
0dev.to
Paradox of choice in design systems.
0dev.to
Global coordination requirements for 2038-class rollover events
0Lobsters

Gentler Streak 6.0 adds a new wellbeing timeline and customizable dashboard
09to5Mac