--- title: What Looked Fine | daily.dev description: A developer reflects on four ML/AI projects and the recurring mistakes made in each. In a skin-care recommendation project (DermAI), an imbalanced dataset... canonical: https://daily.dev/posts/what-looked-fine-0jsjkkbir twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: What Looked Fine | daily.dev og:description: A developer reflects on four ML/AI projects and the recurring mistakes made in each. In a skin-care recommendation project (DermAI), an imbalanced dataset... og:url: https://daily.dev/posts/what-looked-fine-0jsjkkbir og:image: https://api.daily.dev/og/posts/0jSjKkBir.png og:image:alt: What Looked Fine og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # What Looked Fine **[Medium](https://daily.dev/sources/medium_js)** · 7 min read · 0 upvotes · 0 comments ## Summary A developer reflects on four ML/AI projects and the recurring mistakes made in each. In a skin-care recommendation project (DermAI), an imbalanced dataset masked poor model behavior behind acceptable RMSE scores. In a computer vision project (Petrova), YOLO and SAM produced good benchmarks but failed in real-world use due to hardware lag — a problem solved by switching to Apple's native Vision framework. In an LLM-based developer tool (Legit?), conflicting evaluation metrics and data legality constraints reshaped the project's scope. In a video summarization project (ViReel), ROUGE/BERTScore metrics favored Pegasus, but human judgment preferred Llama. The throughline: surface-level metrics often hide deeper problems, and the real lesson — check the foundation before building — repeated across all four projects in different disguises. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [You Probably Know Less About Your Dataset Than You Think](https://daily.dev/posts/you-probably-know-less-about-your-dataset-than-you-think-le5iloq75) · Medium · 0 upvotes · 0 comments - [Making AI work through eval hygiene](https://daily.dev/posts/making-ai-work-through-eval-hygiene-9yhow3tph) · InfoWorld · 0 upvotes · 0 comments - [EvalHub: Because "looks good to me" isn't a benchmark](https://daily.dev/posts/evalhub-because-looks-good-to-me-isn-t-a-benchmark-osnz9ucrd) · Red Hat Developer · 0 upvotes · 0 comments - [The Revenge of the Data Scientist – Hamel’s Blog](https://daily.dev/posts/the-revenge-of-the-data-scientist-hamel-s-blog-flzp9fqrq) · Hacker News · 1 upvotes · 0 comments - [Why Most Machine Learning Projects Fail to Reach Production](https://daily.dev/posts/why-most-machine-learning-projects-fail-to-reach-production-opcx6gdce) · InfoQ · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#data-science](https://daily.dev/tags/data-science), [#llm](https://daily.dev/tags/llm), [#computer-vision](https://daily.dev/tags/computer-vision), [#data-quality](https://daily.dev/tags/data-quality) [View this post on daily.dev](https://daily.dev/posts/what-looked-fine-0jsjkkbir) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"What Looked Fine","url":"https://daily.dev/posts/what-looked-fine-0jsjkkbir","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/what-looked-fine-0jsjkkbir"},"datePublished":"2026-07-12T04:54:31.012Z","dateModified":"2026-07-12T04:56:18.708Z","description":"A developer reflects on four ML/AI projects and the recurring mistakes made in each. In a skin-care recommendation project (DermAI), an imbalanced dataset...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/63a8fa0f6d14d632a1c79ba94ba01023?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/63a8fa0f6d14d632a1c79ba94ba01023?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/what-looked-fine-0jsjkkbir","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,data-science,llm,computer-vision,data-quality","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"What Looked Fine"}]} ```