[{"data":1,"prerenderedAt":480},["ShallowReactive",2],{"project-47990708":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":5,"maker":10,"posted_at":11,"year":12,"points":13,"comments":14,"rank_in_year":15,"shown_in_year":16,"top":17,"tier":18,"category":19,"subcategory":20,"format":21,"keywords":22,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":34,"aspects":35,"strip":44,"post_text":46,"what":47,"said":88,"maker_in_thread":201,"shape":213,"grid":217,"attempts":442,"same_week":443,"maker_shows":45,"maker_hidden":472,"reader_version":473,"card":474},"47990708","hnup.date","State of the Art of Coding Models, According to Hacker News Commenters","title","Show HN: State of the Art of Coding Models, According to Hacker News Commenters","https:\u002F\u002Fhnup.date\u002Fhn-sota","yunusabd",1777757105,2026,168,87,367,4366,9,"notable","ai","model comparison dashboard","web_app",[23,24,25,26],"coding models","hacker news sentiment","llm comparison","ai coding assistants","curious",-0.225,{"positive":30,"neutral":31,"mixed":32,"critical":33},3,14,0,11,28,{"design":36,"execution":39,"idea":40,"docs":43},{"positive":37,"critical":38},1,4,{"positive":32,"critical":37},{"positive":41,"critical":42},2,6,{"positive":32,"critical":32},[30,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,37,45,37,37,30,37,30,41,30,30,30,37,30,37,30,30,30,30,32,30,37,32,32,32],5,"Hello HN,\n\nI was away from my computer for two weeks, and after coming back and reading the latest discussions on HN about coding assistants (models, harnesses), I felt very out of the loop. My normal process would have been to keep reading and figure out the latest and greatest from people's comments, but I wanted to try and automate this process.\n\nBasically the goal is to get a quick overview over which coding models are popular on HN. A next iteration could also scan for harnesses that people use, or info on self-hosting or hardware setups.\n\nI wrote a short intro on the page about the pipel",{"problem":48,"audience":54,"pricing":59,"motivation":60,"time_to_build":59,"stack":64,"openness":85,"stage":86,"team_size":87},{"value":49,"source":50,"evidence":51},"Getting an overview of which coding models are popular on HN without reading every thread","maker",[52],{"id":53},"post",{"value":55,"source":56,"evidence":57},"Developers following coding assistants who want a quick overview of HN discussion","inferred",[58],{"id":53},null,{"value":61,"source":50,"evidence":62},"Maker was away for two weeks and wanted to catch up on coding model discussion automatically",[63],{"id":53},[65,71,75],{"value":66,"source":50,"evidence":67},"Gemini (used for sentiment rating via batch processing)",[68],{"id":69,"by":10,"text":70},"47991376","It's actually ChatGPT at the moment for the first filtering step, for no other reason than having a code snippet ready that I could point Cursor at (I know, so 2025). The Gemini…",{"value":72,"source":50,"evidence":73},"ChatGPT (used for first filtering step)",[74],{"id":69,"by":10,"text":70},{"value":76,"source":50,"evidence":77},"Google Sheets (data store)",[78,82],{"id":79,"by":80,"text":81},"47994965","swyx","> Quota exceeded for quota metric 'Read requests' and limit 'Read requests per minute per user' of service 'sheets.googleapis.com' for consumer 'project_number:849324395320'.…",{"id":83,"by":10,"text":84},"47995546","Didn't expect it to get hammered like that, just added caching for the sheets request. Thanks, my guy ;) Backfilling it further is definitely in the cards, I just want to…","unknown","launched","solo",{"praise":89,"objections":117,"requests":152,"questions":181,"alternatives":196},[90,102],{"value":91,"source":92,"evidence":93},"Useful way to track model sentiment and popularity on HN","commenter",[94,98],{"id":95,"by":96,"text":97},"47993684","gertlabs","This is awesome data! I've been wanting to measure how closely hype aligns to our results at https:\u002F\u002Fgertlabs.com\u002Frankings Subjectively, it seemed like DeepSeek V4 Pro had the…",{"id":99,"by":100,"text":101},"47991974","idivett","Thanks for doing the hard work. I've bookmarked this, hoping it'll come handy when new models are released. If you're taking feature requests, I've a few. - Show combined…",{"value":103,"source":92,"evidence":104},"Open models like Kimi, Qwen and DeepSeek get positive sentiment",[105,109,113],{"id":106,"by":107,"text":108},"47990800","jdw64","Interpreting these metrics is quite interesting. One thing for sure is that while Claude is currently taking the #1 spot in mentions, it carries a lot of negative sentiment due…",{"id":110,"by":111,"text":112},"47991938","2ndorderthought","Interesting to see the positive sentiment around kimi2.6 qwen3.6 and deepseek relative to the negative. I hope the trend of people appreciating open models continue. They aren't…",{"id":114,"by":115,"text":116},"47993558","skeptrune","What a win it is for open source that qwen and kimi show up on this at all.",[118,133,144],{"value":119,"source":92,"evidence":120},"Mention counts and sentiment don't measure actual model quality, only popularity",[121,125,129],{"id":122,"by":123,"text":124},"47991104","ranger_danger","Just FYI this article seems to define \"start of the art\" as \"popular\", as measured by \"total mentions and user sentiment\", without any bearing on the technical abilities or…",{"id":126,"by":127,"text":128},"47991950","gobdovan","Before harnesses, I'd fix the methodology\u002Fclaims. A saner methodology would be to see comments that compare two models, say 'gpt5.5>opus4.7' and infer context ('ctx:frontend',…",{"id":130,"by":131,"text":132},"47995015","input_sh","Terrible metric that tells absolutely nothing about what's state-of-the-art. You might as well call this list the most astroturfed models on HN.",{"value":134,"source":92,"evidence":135},"Graph labels were unreadable and the page is heavy with JavaScript",[136,140],{"id":137,"by":138,"text":139},"47990932","Jabbles","Please fix your graph so the names of the models are readable",{"id":141,"by":142,"text":143},"47991615","pbgcp2026","So, it's a webpage with 3 paragraphs and a simple chart. It has: 1) terrible color scheme – fine, I switch to reader mode 2) shitloads of JS - fine, NoScript works, page breaks…",{"value":145,"source":92,"evidence":146},"Possible astroturfing or bot sentiment skews the results",[147,151],{"id":148,"by":149,"text":150},"47992952","jesse_dot_id","I suspect companies are deploying bots to shift sentiment around their products. I find metrics like this to be largely useless vs. actually just trying stuff out.",{"id":130,"by":131,"text":132},[153,163,167,174],{"value":154,"source":92,"evidence":155},"Graph sentiment over time from model release dates",[156,160],{"id":157,"by":158,"text":159},"47991576","brooksc","It'd be interesting to also graph this over time to see how sentiment changes from when a model is released to today.",{"id":161,"by":10,"text":162},"47992393","Yes! Going forward I'm definitely doing that, once there is enough data. Might even backfill the data more into the past. I just want to stabilize the methodology before burning…",{"value":164,"source":92,"evidence":165},"Combine results by model family or vendor",[166],{"id":99,"by":100,"text":101},{"value":168,"source":92,"evidence":169},"Extend the analysis to coding agents and harnesses",[170],{"id":171,"by":172,"text":173},"48002931","bigbadfeline","How about State of the Art of Coding Agents?",{"value":175,"source":92,"evidence":176},"Show the Gemini prompt used for sentiment rating",[177],{"id":178,"by":179,"text":180},"48039107","Skinless1501","> For each post, sends the title and comments to Gemini I wonder if Gemini has a bias for specific models that could influence those ratings. Might be worth to show the prompt…",[182,189],{"value":183,"source":92,"evidence":184},"Should Claude Opus 4.7 and Claude Opus Latest be merged?",[185],{"id":186,"by":187,"text":188},"47992141","chillfox","Surely \"Claude Opus 4.7\" and \"Claude Opus Latest\" should be the same, right?",{"value":190,"source":92,"evidence":191},"How noisy is the sentiment classification?",[192],{"id":193,"by":194,"text":195},"47992186","Hari2028","How noisy is the sentiment classification? Feels like that could skew results a lot",[197],{"value":198,"source":92,"evidence":199},"Gertlabs rankings for model performance",[200],{"id":95,"by":96,"text":97},{"comments":202,"answered":41,"key":203},10,[204,207,210],{"id":205,"text":206},"47991420","Yep, a toggle to scale all columns to the same height could solve this. I'll look into it when I do the custom graph",{"id":208,"text":209},"47991799","Thanks, I replaced it with a custom graph, should be easier to read now.",{"id":211,"text":212},"47991815","Thanks for the comment, should be fixed now.",{"commenters":214,"max_depth":215,"maker_replies":202,"first_comment_mins":33,"lifespan_hours":216},57,8,92,[218,220,224,227,231,234,237,240,242,245,248,251,254,255,258,260,263,265,267,269,271,274,277,279,282,285,288,291,293,295,297,300,303,306,309,311,314,316,319,322,323,324,327,329,332,335,337,341,344,346,348,350,352,354,355,356,359,362,364,366,370,371,373,377,379,383,385,389,391,395,397,400,402,406,408,411,414,416,419,421,424,427,432,434,438],[106,32,30,219,107,32],"project\u002Fneutral\u002Fnone",[221,32,32,222,223,32],"47991941","commenter\u002Fneutral\u002Fnone","awesome_dude",[225,32,32,226,111,32],"47992001","other\u002Fneutral\u002Fpricing",[228,32,32,229,230,32],"47992090","other\u002Fneutral\u002Fnone","dgacmu",[232,32,32,229,233,32],"47994556","chewz",[235,32,32,229,236,32],"47993211","sgc",[238,32,32,229,239,32],"47993979","uxcolumbo",[241,32,32,229,236,32],"47998628",[243,32,32,229,244,32],"47993697","petesergeant",[246,32,32,229,247,32],"47993840","devmor",[249,32,32,229,250,32],"47994166","dentemple",[252,32,32,226,253,32],"47993883","pryanshu89",[110,37,32,229,111,32],[256,37,32,229,257,32],"47992299","SilverElfin",[259,37,32,229,111,32],"47992388",[261,37,32,222,262,32],"47996319","miyoji",[264,37,32,222,111,32],"47996792",[266,37,32,222,262,32],"47996820",[268,37,32,222,111,32],"47996959",[270,37,32,222,262,32],"47997158",[272,41,32,229,273,32],"47996600","fredcallagan",[275,41,32,229,276,32],"47996886","julianlam",[278,41,32,229,111,32],"47996943",[280,41,32,229,281,32],"48000720","ElectricalUnion",[283,30,32,229,284,32],"47996964","dzink",[286,38,32,226,287,32],"47993031","cheesecakegood",[289,38,32,222,290,32],"47993162","esperent",[292,38,32,222,276,32],"47993442",[294,38,32,222,290,32],"47993561",[296,38,32,229,111,32],"47996840",[298,38,32,229,299,32],"48001481","jiggawatts",[301,38,32,229,302,32],"48005029","vonunov",[304,38,32,229,305,32],"48003993","polishdude20",[307,45,32,229,308,32],"47995084","nonameiguess",[137,42,37,310,138,32],"project\u002Fcritical\u002Fdesign",[312,42,37,310,313,32],"47991093","marcuskaz",[205,42,32,315,10,37],"maker\u002Fneutral\u002Fdesign",[317,42,45,318,313,32],"47991808","maker\u002Fpositive\u002Fdesign",[320,42,37,310,321,32],"47991440","smeej",[208,42,32,315,10,37],[211,42,32,315,10,37],[79,325,37,326,80,32],7,"project\u002Fcritical\u002Fexecution",[83,325,32,328,10,37],"maker\u002Fneutral\u002Fexecution",[330,325,30,315,331,32],"47995976","m0rde",[333,325,30,334,80,32],"48011661","maker\u002Fneutral\u002Fnone",[122,215,37,336,123,32],"project\u002Fcritical\u002Fidea",[338,215,30,339,340,32],"47991199","project\u002Fneutral\u002Fidea","mellosouls",[342,215,32,343,10,37],"47991485","maker\u002Fneutral\u002Fidea",[345,215,37,336,262,32],"47996297",[347,215,37,336,80,32],"47994993",[95,17,45,349,96,32],"project\u002Fpositive\u002Fidea",[351,17,32,334,10,37],"47994017",[186,202,30,353,187,32],"project\u002Fneutral\u002Fexecution",[157,33,30,339,158,32],[161,33,32,328,10,37],[357,33,30,339,358,32],"47994968","itsnewme",[99,360,30,361,100,32],12,"project\u002Fneutral\u002Fdesign",[126,363,37,336,127,32],13,[365,363,32,343,10,37],"47992191",[367,31,30,368,369,32],"47990941","project\u002Fneutral\u002Fdocs","yakkomajuri",[69,31,32,328,10,37],[148,372,37,336,149,32],15,[374,375,32,229,376,32],"48006476",16,"brihati",[178,378,30,353,179,32],17,[380,381,32,229,382,32],"48011713",18,"geopsist",[114,384,45,349,115,32],19,[386,387,32,229,388,32],"47995004",20,"misbau",[141,390,37,310,142,32],21,[392,393,30,219,394,32],"47997323",22,"SpyCoder77",[193,396,30,353,194,32],23,[398,396,32,399,10,37],"47992371","maker\u002Fpositive\u002Fexecution",[171,401,30,339,172,32],24,[403,404,32,229,405,32],"47994406",25,"jatins",[407,404,32,229,276,32],"47997273",[409,410,30,339,276,32],"47993274",26,[412,410,32,222,413,32],"47995857","asnelt",[130,415,37,336,131,32],27,[417,34,32,229,418,32],"47992654","Frannky",[420,34,32,229,418,32],"47992755",[422,34,32,222,423,32],"47994314","alxhslm",[425,34,32,229,426,32],"47994480","rane",[428,429,32,430,431,32],"47993328",29,"commenter\u002Fneutral\u002Fidea","tokkkie",[433,429,32,430,111,32],"47996880",[435,436,32,229,437,32],"47997241",30,"askos",[439,440,32,229,441,32],"47996041",31,"Topfi",[],[444,449,454,458,463,467],{"id":445,"name":446,"points":447,"category":448},"47972511","WhatCable",566,"hardware",{"id":450,"name":451,"points":452,"category":453},"48038257","Hallucinopedia",317,"creative",{"id":455,"name":456,"points":457,"category":453},"48026342","PaletteInspiration",215,{"id":459,"name":460,"points":461,"category":462},"48037724","Tilde.run",205,"dev_tools",{"id":464,"name":465,"points":466,"category":19},"47995037","ml-sharp-web",185,{"id":468,"name":469,"points":470,"category":471},"48038019","Templatical",169,"productivity",false,"v2",{"id":475,"name":5,"line":6,"ai":472,"cat":19,"year":12,"points":13,"comments":14,"rec":27,"s":476,"top":17,"kw":477,"maker":10,"domain":5,"tier":18,"attempts":32,"strip":478,"url":9,"mix":479,"praise":91,"objection":119,"sub":20},47990708,-0.22,[23,24,25,26],"3000000000000000151131323331313333031000",[30,31,32,33],1793991153293]