[{"data":1,"prerenderedAt":130},["ShallowReactive",2],{"project-37354204":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":28,"sentiment":29,"stance_mix":30,"scored_comments":32,"aspects":33,"strip":35,"post_text":36,"what":37,"said":61,"maker_in_thread":79,"shape":82,"grid":86,"attempts":94,"same_week":95,"maker_shows":122,"maker_hidden":123,"reader_version":124,"card":125},"37354204","datalens","Automating Job Search with AI","title","Show HN: Automating Job Search with AI","https:\u002F\u002Fgithub.com\u002FAdrianKrebs\u002Fdatalens","github.com","hubraumhugo",1693591283,2023,34,3,1315,3109,43,"shown","ai","job search ranking","other",[24,25,26,27],"llm job search","job posting ranking","hacker news who's hiring","ai job matching","quiet",null,{"positive":31,"neutral":32,"mixed":31,"critical":31},0,1,{"execution":34},{"positive":31,"critical":31},[15,31,31],"This is a personal experiment that uses LLMs to rank unstructured job posting data based on user-defined criteria. Traditional job search platforms rely on rigid filtering systems, but many users lack such concrete criteria.\n\nOne of the superpowers of LLMs is understanding unstructured data, like the job postings in the monthly \"Ask HN: who's hiring\" threads. So i built a little tool that lets you define your preferences in a more natural way and then rates each job postings based on the relevance.\n\nIt's far from perfect (especially with gpt-3.5), but still helps to cut through a lot of noise.",{"problem":38,"audience":29,"pricing":29,"motivation":44,"time_to_build":29,"stack":48,"openness":59,"stage":60,"team_size":59},{"value":39,"source":40,"evidence":41},"Job searches rely on rigid filters, and many users lack concrete criteria; the tool ranks unstructured postings by relevance.","maker",[42],{"id":43},"post",{"value":45,"source":40,"evidence":46},"Personal experiment to cut through noise in job postings.",[47],{"id":43},[49,53],{"value":50,"source":40,"evidence":51},"LLMs (gpt-3.5)",[52],{"id":43},{"value":54,"source":40,"evidence":55},"Kadoa for generating job scrapers",[56],{"id":57,"by":11,"text":58},"37368363","I'm using https:\u002F\u002FKadoa.com to generate scrapers for any job source in seconds, which removes the bottleneck of having to write and maintain custom code for ever source.","unknown","prototype",{"praise":62,"objections":63,"requests":72,"questions":73,"alternatives":78},[],[64],{"value":65,"source":66,"evidence":67},"Scraping many job sites needs custom code for each site.","commenter",[68],{"id":69,"by":70,"text":71},"37366908","hughdbrown","As I read it, the code scans listed websites for jobs and scrapes the jobs from each page, possibly using custom code, Is that right? That seems to be the weakness of scraping…",[],[74],{"value":75,"source":66,"evidence":76},"Does the code scrape each listed website with custom code?",[77],{"id":69,"by":70,"text":71},[],{"comments":32,"answered":32,"key":80},[81],{"id":57,"text":58},{"commenters":15,"max_depth":83,"maker_replies":32,"first_comment_mins":84,"lifespan_hours":85},2,1880,37,[87,89,93],[69,31,15,88,70,31],"project\u002Fneutral\u002Fexecution",[90,31,31,91,92,31],"37367641","commenter\u002Fneutral\u002Fexecution","tough",[57,31,31,88,11,32],[],[96,101,105,109,114,118],{"id":97,"name":98,"points":99,"category":100},"37408150","smolsite.zip",602,"dev_tools",{"id":102,"name":103,"points":104,"category":100},"37391848","Puck",451,{"id":106,"name":107,"points":108,"category":100},"37393099","RecipeUI",275,{"id":110,"name":111,"points":112,"category":113},"37381268","Keep",181,"infrastructure",{"id":115,"name":116,"points":117,"category":100},"37364124","Shaq",155,{"id":119,"name":120,"points":121,"category":20},"37398812","Perplexity",153,14,false,"v2",{"id":126,"name":5,"line":6,"ai":123,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":127,"maker":11,"domain":10,"tier":19,"attempts":31,"strip":128,"url":9,"mix":129,"praise":-1,"objection":65,"sub":21},37354204,[24,25,26,27],"300",[31,32,31,31],1794036641128]