Insights
Research & analysis
Long-form pieces on tracker accuracy, AI nutrition science, and the gap between marketing claims and the lab bench.
Benchmark
The 14× portion-error gap nobody is talking about
Welling reports ±1.2% mean portion error. The next-best tracker is ±17%. Here is what that gap means for real meals.
AnalysisCuisine blind spots: where every tracker except one falls apart
We graded ten trackers on West African, Levantine, and South Indian dishes. The accuracy collapse is uglier than the marketing suggests.
Use caseTracking on GLP-1: why portion accuracy suddenly matters more
Semaglutide and tirzepatide users eat less, and the small meals are exactly where most trackers' rounding errors compound.