“The question isn’t whether small models are perfect. It’s whether they’re useful enough to build with.” […]
“You don’t need a data center to run useful AI anymore. That changes everything.” I remember […]
After selecting an appropriate model for structured extraction, inconsistencies in output still persisted within the ReceiptFlow […]
When building ReceiptFlow, the goal was simple: take messy OCR output from receipts and convert it […]