[{"data":1,"prerenderedAt":170},["ShallowReactive",2],{"project-20374800":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":33,"aspects":34,"strip":38,"post_text":40,"what":41,"said":44,"maker_in_thread":102,"shape":104,"grid":109,"attempts":135,"same_week":136,"maker_shows":33,"maker_hidden":163,"reader_version":164,"card":165},"20374800","python_autocomplete","Autocomplete Python with Deep Learning","title","Show HN: Autocomplete Python with Deep Learning","https:\u002F\u002Fgithub.com\u002Fvpj\u002Fpython_autocomplete","github.com","vpj",1562502961,2019,109,11,442,2195,21,"notable","ai","code completion","library",[24,25,26,27],"python autocomplete","deep learning code completion","character language model","code prediction","curious",0,{"positive":31,"neutral":32,"mixed":29,"critical":31},1,5,7,{"idea":35,"docs":36,"performance":37},{"positive":31,"critical":31},{"positive":29,"critical":29},{"positive":29,"critical":29},[32,29,39,39,39,39,29,29,39,31],3,null,{"problem":40,"audience":40,"pricing":40,"motivation":40,"time_to_build":40,"stack":42,"openness":43,"stage":43,"team_size":43},[],"unknown",{"praise":45,"objections":54,"requests":69,"questions":77,"alternatives":92},[46],{"value":47,"source":48,"evidence":49},"Interesting idea, could be used for phone coding keyboards","commenter",[50],{"id":51,"by":52,"text":53},"20376836","bobajeff","I've been thinking about using something like this for Swype-like keyboard for coding on phones.",[55,62],{"value":56,"source":48,"evidence":57},"Commenter questions whether it beats language server completion like RLS",[58],{"id":59,"by":60,"text":61},"20377026","logicprog","This is pretty cool, but I'm not sure how much better this approach would be compared to language server based completion (something like RLS).",{"value":63,"source":48,"evidence":64},"Simple neural networks are not best for code; n-gram models reach similar accuracy",[65],{"id":66,"by":67,"text":68},"20375084","veselin","This one is a character level language model. The Microsoft one is per token. This one should be the closest to the Microsoft model:…",[70],{"value":71,"source":48,"evidence":72},"Online demo or Jupyter notebook with downloadable pretrained model",[73],{"id":74,"by":75,"text":76},"20377809","make3","I wished they had an online demo, or jupyter notebook with an easy to download pretrained model so I can test it in colab",[78,85],{"value":79,"source":48,"evidence":80},"How does it differ from Microsoft's IntelliCode?",[81],{"id":82,"by":83,"text":84},"20375045","nikeee","Is this similar to Microsoft's IntelliCode? How does it differ?",{"value":86,"source":48,"evidence":87},"Would GPT-2 be used for this?",[88],{"id":89,"by":90,"text":91},"20375458","p1esk","What about gpt-2?",[93,98],{"value":94,"source":48,"evidence":95},"Microsoft IntelliCode",[96,97],{"id":82,"by":83,"text":84},{"id":66,"by":67,"text":68},{"value":99,"source":48,"evidence":100},"Language server completion (RLS)",[101],{"id":59,"by":60,"text":61},{"comments":29,"answered":29,"key":103},[],{"commenters":105,"max_depth":106,"maker_replies":29,"first_comment_mins":107,"lifespan_hours":108},9,4,71,12,[110,112,116,120,123,124,126,130,132,133],[51,29,32,111,52,29],"project\u002Fpositive\u002Fidea",[113,29,29,114,115,29],"20377584","other\u002Fneutral\u002Fnone","sho",[117,31,39,118,119,29],"20379024","project\u002Fneutral\u002Fidea","etaioinshrdlu",[74,121,39,122,75,29],2,"project\u002Fneutral\u002Fdocs",[82,39,39,118,83,29],[66,39,39,125,67,29],"project\u002Fneutral\u002Fperformance",[127,39,29,128,129,29],"20375379","commenter\u002Fneutral\u002Fnone","ma2rten",[131,39,29,128,90,29],"20375467",[89,39,39,118,90,29],[59,106,31,134,60,29],"project\u002Fcritical\u002Fidea",[],[137,142,146,150,155,158],{"id":138,"name":139,"points":140,"category":141},"20355477","Effortless",191,"productivity",{"id":143,"name":144,"points":145,"category":141},"20365436","Hoxly News",154,{"id":147,"name":148,"points":145,"category":149},"20376437","Bvckup 2","infrastructure",{"id":151,"name":152,"points":153,"category":154},"20373560","Old School Graphics Algorithms",126,"languages",{"id":156,"name":157,"points":153,"category":20},"20392342","GPT-2 MTG card generator",{"id":159,"name":160,"points":161,"category":162},"20379026","Comntr",84,"dev_tools",false,"v2",{"id":166,"name":5,"line":6,"ai":163,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":167,"maker":11,"domain":10,"tier":19,"attempts":29,"strip":168,"url":9,"mix":169,"praise":47,"objection":56,"sub":21},20374800,[24,25,26,27],"5033330031",[31,32,29,31],1794036578948]