[{"data":1,"prerenderedAt":125},["ShallowReactive",2],{"project-40248744":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":31,"aspects":32,"strip":34,"post_text":36,"what":37,"said":56,"maker_in_thread":74,"shape":77,"grid":79,"attempts":84,"same_week":89,"maker_shows":15,"maker_hidden":118,"reader_version":119,"card":120},"40248744","Cocoon","An open-source tool that semantically profiles your data using LLMs","title","Show HN: An open-source tool that semantically profiles your data using LLMs","https:\u002F\u002Fgithub.com\u002FCocoon-Data-Transformation\u002Fcocoon","github.com","zh2408",1714749854,2024,10,2,2671,3515,76,"shown","data","data profiling","web_app",[21,24,25,26],"csv anomaly detection","llm data quality","table profiling","quiet",null,{"positive":30,"neutral":30,"mixed":31,"critical":30},0,1,{"execution":33},{"positive":30,"critical":30},[35,30],3,"The problem we solve is profiling tables: this is the initial step where you need to understand the table and identify any anomalies.\n\nDuring the process, many small decisions require semantic understanding. For example, missing values are normal for 'deathdate' (still alive) but abnormal for 'name.' For outliers, 100 for ages is fine, but some are -1, which is impossible! We use LLMs to semantically understand your tables and detect anomalies.\n\nYou can try it by uploading a CSV, and we will email back the profile: https:\u002F\u002Fcocoon-data-transformation.github.io\u002Fpage\u002F\n\nLet me know your feedback. ",{"problem":38,"audience":28,"pricing":28,"motivation":44,"time_to_build":28,"stack":48,"openness":55,"stage":55,"team_size":55},{"value":39,"source":40,"evidence":41},"Profiling tables to understand them and spot anomalies, where semantic context decides what counts as normal","maker",[42],{"id":43},"post",{"value":45,"source":40,"evidence":46},"Profiling tables is a first step that needs semantic understanding, such as telling missing deathdate values from missing names",[47],{"id":43},[49],{"value":50,"source":40,"evidence":51},"Claude 3",[52],{"id":53,"by":11,"text":54},"40249375","Thank you so much! I'll fix the warning. Yes, that's an issue with LLMs. I'm using Claude 3, which was trained on data up to August 2023. I'll add the current date in the prompt.…","unknown",{"praise":57,"objections":58,"requests":67,"questions":72,"alternatives":73},[],[59],{"value":60,"source":61,"evidence":62},"Browser shows insecure form warnings on submit","commenter",[63],{"id":64,"by":65,"text":66},"40249297","haidousm","cool project. getting insecure form warnings when submitting. you'll want to spin up an ingress (nginx, ..) to front your requests & use TLS (let's encrypt) edit: the CSV i used…",[68],{"value":69,"source":61,"evidence":70},"Serve the form over TLS behind an ingress such as nginx",[71],{"id":64,"by":65,"text":66},[],[],{"comments":31,"answered":30,"key":75},[76],{"id":53,"text":54},{"commenters":15,"max_depth":15,"maker_replies":31,"first_comment_mins":78,"lifespan_hours":31},47,[80,82],[64,30,35,81,65,30],"project\u002Fmixed\u002Fexecution",[53,30,30,83,11,31],"maker\u002Fneutral\u002Fexecution",[85,86],{"id":4,"t":12,"points":14,"comments":15},{"id":87,"t":88,"points":31,"comments":30},"40381178",1715881723,[90,95,99,104,109,114],{"id":91,"name":92,"points":93,"category":94},"40252569","Secret Llama",547,"ai",{"id":96,"name":97,"points":98,"category":94},"40300126","GrafyChat",459,{"id":100,"name":101,"points":102,"category":103},"40250557","BandMatch",452,"productivity",{"id":105,"name":106,"points":107,"category":108},"40260035","Dillo",430,"dev_tools",{"id":110,"name":111,"points":112,"category":113},"40273470","GetAnyPlant",427,"consumer_social",{"id":115,"name":116,"points":117,"category":94},"40272339","AI climbing coach",320,false,"v2",{"id":121,"name":5,"line":6,"ai":118,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":28,"top":18,"kw":122,"maker":11,"domain":10,"tier":19,"attempts":15,"strip":123,"url":9,"mix":124,"praise":-1,"objection":60,"sub":21},40248744,[21,24,25,26],"30",[30,30,31,30],1794036654196]