LLM Food Recognition in Production: What Shipping soba Taught Me

·1 views

TL;DR I spent the last few months building soba, an iOS app that photographs a meal and returns carbs, glycemic index, and portion weights for people who count carbohydrates. The recognition backend went through one model migration, one full prompt rewrite, and a stack of validation code. Three things carried almost all of the improvement: picking the model with a benchmark instead of vibes, forcing strict JSON Schema through OpenRouter, and rewriting the prompt around scene scale rather than food identity. Model choice turned out to be the smallest lever of the three. Every model I tested mis

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Monitoring AI coding agent costs and activity on your own machine

I run Claude Code, Cursor, Codex and a handful of sub-agents on my own machines every day. For a long time, I knew what they cost but had little visibility into their work. If an agent felt slow or got stuck, I had to dig through separate logs to understand why. That became harder as I started using several agents on the same project. Each kept its own session history, and there was no single place to review the activity.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Autoscaling doesn't save you at 30,000 requests per second — your dependencies do

There's a comfortable story about peak traffic: load goes up, the autoscaler notices, pods multiply, everyone keeps their evening. I've watched that story hold, and I've watched it fail in a specific and instructive way — the autoscaler worked perfectly and the platform degraded anyway. Running transaction paths at sustained peaks in the tens of thousands of requests per second teaches you that horizontal scaling is the easy half of the problem. The hard half is that everything your new pods talk to did not scale, and now there are more of them asking. Scale-up triggers.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

What If an AI Could Answer a Legal Question Based on the Law That Existed At That Time?

What If an AI Could Answer a Legal Question Based on the Law That Existed At That Time? I've been working on a research project called Indian Constitution Temporal QA, and it started with a question that sounds simple: Can an AI answer a question about the Indian Constitution while taking the date of the question into account? Most question-answering systems treat a document as if it is static. Legal documents aren't. The Indian Constitution has been amended repeatedly.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

A cache key ate 99.9% of my records and the pipeline looked green

The worst pipeline bug I've shipped didn't throw. No stack trace, no failed job, no alert. Every run went green, finished inside its window, and wrote roughly one record out of every thousand it was handed. The job's own metrics said it was healthy, because the job's own metrics counted runs, not rows. It took a business user asking why a campaign list looked short to surface it.

0 comments Read more at DEV Community