[{"data":1,"prerenderedAt":266},["ShallowReactive",2],{"project-36574090":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":34,"aspects":35,"strip":42,"post_text":43,"what":44,"said":86,"maker_in_thread":167,"shape":178,"grid":182,"attempts":227,"same_week":228,"maker_shows":179,"maker_hidden":258,"reader_version":259,"card":260},"36574090","JobLens","AI-powered job search for 'Who Is Hiring'","title","Show HN: JobLens – AI-powered job search for 'Who Is Hiring'","https:\u002F\u002Fwww.kadoa.com\u002Fjoblens","kadoa.com","hubraumhugo",1688397384,2023,108,18,594,3109,20,"notable","web_saas","job search","web_app",[21,24,25,26],"who is hiring","hacker news jobs","gpt job matching","mixed",-0.034,{"positive":30,"neutral":31,"mixed":32,"critical":33},3,5,1,4,13,{"execution":36,"design":39,"idea":40,"performance":41},{"positive":37,"critical":38},2,0,{"positive":38,"critical":30},{"positive":32,"critical":38},{"positive":38,"critical":32},[31,38,38,38,32,30,38,31,30,32,30,32,30,38,31,32,30,30],"There are existing HN job aggregators, but I thought we could take it a step further.\nInspired by an insightful comment on a previous thread (https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=36163021), I built a tool that aggregates job postings and intelligently categorizes them based on user-specific preferences:\n\n* Country and remote work preferences\n\n* Employer type (e.g., startup, corporation, government)\n\n* Industry\n\n* Technologies used\n\n* Role type (developer, architect, product owner, etc.)\n\n* Salary range (where available)\n\nOne of the superpowers of LLMs is reformatting information from any forma",{"problem":45,"audience":51,"pricing":60,"motivation":61,"time_to_build":60,"stack":65,"openness":84,"stage":85,"team_size":84},{"value":46,"source":47,"evidence":48},"Finding relevant jobs in HN Who Is Hiring threads without manual filtering","maker",[49],{"id":50},"post",{"value":52,"source":53,"evidence":54},"Developers and tech workers searching for jobs","inferred",[55,56],{"id":50},{"id":57,"by":58,"text":59},"36578062","boxcarr","JobLens is cool! This past month we had the same idea -- it's been a fun project: https:\u002F\u002Fhnjobs.u-turn.dev ChatGPT does an incredible job parsing, but then lots of effort goes…",null,{"value":62,"source":47,"evidence":63},"Take existing HN job aggregators a step further with personalized filters",[64],{"id":50},[66,73,80],{"value":67,"source":47,"evidence":68},"OpenAI GPT functions",[69,70],{"id":50},{"id":71,"by":11,"text":72},"36578176","Yes, you can essentially use GPT functions to reliably output JSON based on a predefined schema. See…",{"value":74,"source":75,"evidence":76},"gpt-3.5-turbo","commenter",[77],{"id":78,"by":58,"text":79},"36579188","Not sure if you found this as well, but gpt-3.5-turbo-016 does a poor job following instructions other than parsing. So, to work around this, we prompt gpt-3.5-turbo with the…",{"value":81,"source":47,"evidence":82},"Embeddings",[83],{"id":50},"unknown","launched",{"praise":87,"objections":103,"requests":126,"questions":142,"alternatives":154},[88,96],{"value":89,"source":75,"evidence":90},"Results look good and LLM parsing works well",[91,92],{"id":57,"by":58,"text":59},{"id":93,"by":94,"text":95},"36578306","SCUSKU","Wow this is amazing. This is more or less what I was trying to build https:\u002F\u002Fhnresumetojobs.com to look like, I am reconsidering whether or not to continue now. I tried using the…",{"value":97,"source":75,"evidence":98},"Good example of structured extraction with OpenAI functions",[99],{"id":100,"by":101,"text":102},"36580247","mmaia","Looks like it's getting some fields wrong. For examples, \"Global\" location is matching other text not related to the job location. Still, a good example of OpenAI's functions. I…",[104,115,119],{"value":105,"source":75,"evidence":106},"Must pick from a long industry list before searching, causing abandonment",[107,111],{"id":108,"by":109,"text":110},"36579954","version_five","Hi, just a thought, I backed out as soon as I saw I had to pick from a giant list of industries. Most people don't have rigid criteria like that, and if the do, a conventional…",{"id":112,"by":113,"text":114},"36586381","dsgnr","Need a category for design. Right now all design jobs are scattered around, mostly in product management. Also as others have mentioned, having to make all these decisions before…",{"value":116,"source":75,"evidence":117},"Some fields extracted wrong, e.g. Global location",[118],{"id":100,"by":101,"text":102},{"value":120,"source":75,"evidence":121},"Checkmark on unchecked options is confusing",[122],{"id":123,"by":124,"text":125},"36580195","SomewhatLikely","Having the 'unchecked' visual actually have a checkmark threw me off. I was thinking, oh goodness, I have to deselect all of these.",[127,131,135],{"value":128,"source":75,"evidence":129},"Conversational or freeform search instead of rigid filters",[130],{"id":108,"by":109,"text":110},{"value":132,"source":75,"evidence":133},"Add a design job category",[134],{"id":112,"by":113,"text":114},{"value":136,"source":75,"evidence":137},"Support sites that require login such as LinkedIn",[138],{"id":139,"by":140,"text":141},"36579982","digitalsanctum","I was going to build something similar for funsies but now I don't have to :) I'm curious the page mentions not being able to scrape sites that require a login but then I saw…",[143,147],{"value":144,"source":75,"evidence":145},"How to reduce hallucination in structured extraction",[146],{"id":93,"by":94,"text":95},{"value":148,"source":75,"evidence":149},"Is there similar tool for freelancing gigs",[150],{"id":151,"by":152,"text":153},"36578563","baxtr","Nice! Is there something similar for freelancing gigs?",[155,159,163],{"value":156,"source":75,"evidence":157},"hnjobs.u-turn.dev",[158],{"id":57,"by":58,"text":59},{"value":160,"source":75,"evidence":161},"hnresumetojobs.com",[162],{"id":93,"by":94,"text":95},{"value":164,"source":75,"evidence":165},"aijobnetwork.com",[166],{"id":100,"by":101,"text":102},{"comments":33,"answered":32,"key":168},[169,172,175],{"id":170,"text":171},"36578149","Your project looks quite impressive as well, especially the extracted URLs to apply and the candidate profiles, didn't get that far yet :) Automating tedious work like data…",{"id":173,"text":174},"36583408","yeah I had the same experience, divide and conquer works better than trying to do everything with a single prompt. Are you interested in comparing notes? Feel free to ping me via…",{"id":176,"text":177},"36582477","You're right, I'll improve this.",{"commenters":179,"max_depth":33,"maker_replies":33,"first_comment_mins":180,"lifespan_hours":181},14,264,22,[183,185,187,189,190,192,196,198,199,203,204,206,207,211,212,215,220,223],[57,38,31,184,58,38],"project\u002Fpositive\u002Fexecution",[170,38,38,186,11,32],"maker\u002Fpositive\u002Fexecution",[78,38,38,188,58,38],"commenter\u002Fneutral\u002Fnone",[173,38,38,188,11,32],[108,32,32,191,109,38],"project\u002Fcritical\u002Fdesign",[193,32,30,194,195,38],"36582012","project\u002Fneutral\u002Fdesign","great_psy",[176,32,38,197,11,32],"maker\u002Fneutral\u002Fdesign",[93,37,31,184,94,38],[200,37,30,201,202,38],"36580138","maker\u002Fneutral\u002Fexecution","OccamsMirror",[123,37,32,191,124,38],[100,30,30,205,101,38],"project\u002Fmixed\u002Fexecution",[112,33,32,191,113,38],[208,31,30,209,210,38],"36577828","project\u002Fneutral\u002Fexecution","rahimnathwani",[71,31,38,201,11,32],[139,213,31,214,140,38],6,"project\u002Fpositive\u002Fidea",[216,217,32,218,219,38],"36578448",7,"project\u002Fcritical\u002Fperformance","timhigins",[151,221,30,222,152,38],8,"project\u002Fneutral\u002Fidea",[224,225,30,222,226,38],"36579997",9,"Laaas",[],[229,234,239,244,249,254],{"id":230,"name":231,"points":232,"category":233},"36605493","Hacker News user blogroll",937,"consumer_social",{"id":235,"name":236,"points":237,"category":238},"36582468","Degrees What",171,"dev_tools",{"id":240,"name":241,"points":242,"category":243},"36591767","varun.ca",159,"creative",{"id":245,"name":246,"points":247,"category":248},"36590834","FerretDB",147,"data",{"id":250,"name":251,"points":252,"category":253},"36520410","Windmill knowledge base Discord bot",144,"ai",{"id":255,"name":256,"points":257,"category":253},"36564923","Project S.A.T.U.R.D.A.Y.",121,false,"v2",{"id":261,"name":5,"line":6,"ai":258,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":262,"top":18,"kw":263,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":264,"url":9,"mix":265,"praise":89,"objection":105,"sub":21},36574090,-0.03,[21,24,25,26],"500013053131305133",[30,31,32,33],1794036637869]