{"slug": "building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado", "title": "Building OopsCalorie: When Your AI Thinks Dinuguan Is Champorado 😂", "summary": "A developer building OopsCalorie, an AI-powered calorie and meal tracking app, shared early testing challenges where the AI misidentified Filipino dishes like dinuguan as champorado and bagnet as lumpiang shanghai. The project is evolving to incorporate user context, confidence scoring, and food candidate options to handle ambiguous regional foods. The app is currently in testing, with Android and iOS versions coming soon.", "body_md": "I’ve been building a side project called **OopsCalorie**, an AI-powered calorie and meal tracking app.\n\nThe idea sounded simple enough:\n\nSimple, right?\n\nWell...\n\nThen we started testing it with Filipino food. 😂\n\nOne of the funniest parts of building OopsCalorie has been testing the food recognition.\n\nAt one point, our AI confidently looked at **dinuguan** and decided:\n\nThat's champorado.\n\nOkay. I can *kind of* see where you were coming from. Both are dark, both can be served in a bowl...\n\nBut still. 😂\n\nThen came **bagnet**.\n\nAI:\n\nLumpiang Shanghai.\n\nBro.\n\nNot even close. 😂\n\nThese bugs are funny, but they also exposed one of the more interesting engineering problems behind OopsCalorie:\n\n**Image recognition is only the first step.**\n\nCorrectly identifying a meal — especially regional dishes — requires much more context than I initially expected.\n\nWhen I started the project, I thought the difficult part would be estimating calories.\n\nTurns out, before you can estimate:\n\n**You need to know what the food actually is.**\n\nAnd food can be surprisingly ambiguous from an image.\n\nA photo might contain:\n\nEven humans sometimes need context.\n\n*\"Is that pork adobo or humba?\"*\n\n*\"Is that fried pork belly or bagnet?\"*\n\nNow imagine asking an AI to determine that from pixels alone.\n\nThis changed how I'm approaching the system.\n\nInstead of treating the AI response as absolute truth, OopsCalorie is evolving toward a workflow where AI provides an intelligent estimate while the user still has the ability to provide context and correct it.\n\nWe're experimenting with things like:\n\n**Image + user context**\n\nA short description from the user can dramatically reduce ambiguity.\n\n**Confidence scoring**\n\nIf the system isn't confident about what it's looking at, it shouldn't pretend that it is.\n\n**Food candidates**\n\nInstead of saying:\n\nThis is definitely X.\n\nThe system can consider multiple possible foods before making the final estimate.\n\n**Filipino food awareness**\n\nThis is particularly important for us.\n\nA lot of calorie trackers are built around foods that are easy to find in international nutrition databases.\n\nBut Filipino meals aren't always that straightforward.\n\nTry estimating the calories of someone's homemade adobo where every household has a slightly different recipe. 😅\n\nOopsCalorie is currently being built with:\n\nThe goal isn't to build another massive nutrition database with an AI label slapped on top.\n\nI'm more interested in exploring how AI can make food logging feel less like data entry.\n\nTake a photo. Give it some context if necessary. Get an estimate. Correct it when needed. Move on with your day.\n\nOopsCalorie is currently in the **testing phase**.\n\nAnd that's exactly why I'm sharing it now.\n\nI want developers and early users to break it.\n\nUpload weird meals.\n\nUpload Filipino food.\n\nConfuse the AI.\n\nFind edge cases I haven't thought about.\n\nAnd yes, if you manage to make it identify **lechon as a croissant**, please send me the screenshot. 😂\n\nThe Android and iOS versions are coming soon.\n\n🌐 **Website**\n\n[https://oopscalorie.com/](https://oopscalorie.com/)\n\n🧪 **Become a beta tester**\n\n[https://oopscalorie.com/beta-testers](https://oopscalorie.com/beta-testers)\n\n📖 **Development stories & experiments**\n\n[https://oopscalorie.com/blog](https://oopscalorie.com/blog)\n\nI'm also open to collaborations with developers, designers, nutrition/fitness people, or anyone interested in experimenting with AI-powered consumer apps.\n\nOne thing this project keeps reminding me:\n\n**AI can be incredibly impressive and incredibly stupid within the same five minutes.**\n\nAnd honestly, that's part of what makes building with it fun.\n\nEvery ridiculous result becomes another edge case.\n\nEvery edge case becomes another improvement.\n\nAnd every improvement gets us a little closer to making OopsCalorie actually useful.\n\nI'll be sharing more about the technical decisions, AI experiments, failures, costs, architecture, and the occasional food-recognition disaster as development continues.\n\nUntil then...\n\n**Dinuguan is not champorado.**\n\nWe're working on it. 😂", "url": "https://wpnews.pro/news/building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado", "canonical_source": "https://dev.to/chimkennuggyszdev/building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado-4961", "published_at": "2026-08-18 03:29:45+00:00", "updated_at": "2026-08-18 03:42:50.228749+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-products", "ai-tools"], "entities": ["OopsCalorie"], "alternates": {"html": "https://wpnews.pro/news/building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado", "markdown": "https://wpnews.pro/news/building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado.md", "text": "https://wpnews.pro/news/building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado.txt", "jsonld": "https://wpnews.pro/news/building-oopscalorie-when-your-ai-thinks-dinuguan-is-champorado.jsonld"}}