[{"data":1,"prerenderedAt":1061},["ShallowReactive",2],{"project-37125118":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":29,"sentiment":30,"stance_mix":31,"scored_comments":36,"aspects":37,"strip":48,"post_text":50,"what":51,"said":81,"maker_in_thread":204,"shape":215,"grid":218,"attempts":1023,"same_week":1024,"maker_shows":18,"maker_hidden":1053,"reader_version":1054,"card":1055},"37125118","Outlines","LLMs can generate valid JSON 100% of the time","title","Show HN: LLMs can generate valid JSON 100% of the time","https:\u002F\u002Fgithub.com\u002Fnormal-computing\u002Foutlines","github.com","remilouf",1692039174,2023,854,303,10,3109,1,"legend","ai","constrained llm text generation","library",[24,25,26,27,28],"constrained generation","llm json output","regex guided generation","pydantic llm","logit masking","curious",-0.107,{"positive":32,"neutral":33,"mixed":34,"critical":35},20,63,2,30,115,{"idea":38,"performance":41,"execution":43,"docs":46,"design":47},{"positive":39,"critical":40},12,21,{"positive":42,"critical":42},4,{"positive":44,"critical":45},0,3,{"positive":18,"critical":34},{"positive":44,"critical":44},[45,45,44,44,44,44,44,45,18,42,34,34,18,18,18,18,45,49,18,45,45,49,42,45,42,34,34,44,34,45,42,42,42,45,45,18,18,44,18,18],5,"Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming.\n\nRecently we came up with a fast way to generate text that matches a regex (https:\u002F\u002Fblog.normalcomputing.ai\u002Fposts\u002F2023-07-27-regex-guided-generation\u002Fregex-guided-generation.html). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) re",{"problem":52,"audience":58,"pricing":58,"motivation":59,"time_to_build":58,"stack":63,"openness":78,"stage":79,"team_size":80},{"value":53,"source":54,"evidence":55},"LLM output often fails to match a required format such as valid JSON","maker",[56],{"id":57},"post",null,{"value":60,"source":54,"evidence":61},"Authors wanted to understand how the LLM generation process works",[62],{"id":57},[64,68,72],{"value":65,"source":54,"evidence":66},"Python",[67],{"id":57},{"value":69,"source":54,"evidence":70},"Pydantic",[71],{"id":57},{"value":73,"source":54,"evidence":74},"transformers",[75],{"id":76,"by":11,"text":77},"37126636","It can be used with any open source model (if you can get the logits), and to some extent with OpenAI's API. Here is an example with `transformers`:…","open_source","unknown","team",{"praise":82,"objections":93,"requests":127,"questions":146,"alternatives":169},[83],{"value":84,"source":85,"evidence":86},"Masking approach is efficient, with index built once and fast per-step lookups","commenter",[87,90],{"id":88,"by":11,"text":89},"37125974","Thanks for bringing clownfish and relm to my attention! afaik other libraries loop over the entire vocabulary at every step of the generation. We on the other hand build an index…",{"id":91,"by":11,"text":92},"37125656","Two differences: (1) This feature only requires regex-guided generation. We have a PR for BNF sampling that is about to be merged. (2) ggml loops over the entire vocabulary (~50k…",[94,105,116],{"value":95,"source":85,"evidence":96},"Masking may distort the model's probability distribution and hurt output quality",[97,101],{"id":98,"by":99,"text":100},"37131269","hansvm","A major part of the power of an LLM is the calibrated probability distribution in its responses, and this technique probably throws that ability away. Why is it good enough? As a…",{"id":102,"by":103,"text":104},"37126385","aduffy","This is exciting, we built a similar tool[1] recently specifically targeted at constraining llama output to match a TypeScript interface. I firmly believe that output format…",{"value":106,"source":85,"evidence":107},"Valid JSON does not mean correct content",[108,112],{"id":109,"by":110,"text":111},"37125950","Animats","OK, you get syntactically valid JSON, but does it contain the correct info? This is effectively a polisher, like spell check, which gives the output superficially correct form…",{"id":113,"by":114,"text":115},"37126291","tantalor","\"Generating valid JSON\" is not impressive. Here's some valid JSON: [] The tricky part is generating useful JSON.",{"value":117,"source":85,"evidence":118},"Prior similar libraries already exist",[119,123],{"id":120,"by":121,"text":122},"37125874","BoorishBears","I'm not sure how this is different than: https:\u002F\u002Fgithub.com\u002F1rgs\u002Fjsonformer or https:\u002F\u002Fgithub.com\u002Fnewhouseb\u002Fclownfish or https:\u002F\u002Fgithub.com\u002Fmkuchnik\u002Frelm or…",{"id":124,"by":125,"text":126},"37127291","lefttoreader","The “trick” seems to blatantly rip off FlashText without citing it? https:\u002F\u002Farxiv.org\u002Fpdf\u002F1711.00046.pdf I’m a fan of the approach. I normally wouldn’t care if this was just…",[128,135],{"value":129,"source":85,"evidence":130},"Integration with llama.cpp",[131],{"id":132,"by":133,"text":134},"37129909","haolez","Can I use this locally with models that run on my CPU? Like llama.cpp",{"value":136,"source":85,"evidence":137},"Tutorial for running locally with llama2",[138,142],{"id":139,"by":140,"text":141},"37128512","dvasdekis","Would love to have a tutorial on how to install and run this locally with a nice model, for those of us who are behind the 8-ball with torch, transformers, diffusers, llama2 etc.",{"id":143,"by":144,"text":145},"37127577","coder543","As a more general comment, the repo README provides examples that all use gpt2. It would be nice to see at least one example that invokes llama2, since I feel like that would…",[147,158],{"value":148,"source":85,"evidence":149},"Does it work with GPT-4 or OpenAI's API",[150,154],{"id":151,"by":152,"text":153},"37126824","nikcheerla","Does this work with GPT-4?",{"id":155,"by":156,"text":157},"37127145","simonw","I really hope OpenAI add something like this to their endpoints soon. Being able to pass up some kind of grammar (a regular expression, or a JSON schema, or some other format)…",{"value":159,"source":85,"evidence":160},"How much latency does it add",[161,165],{"id":162,"by":163,"text":164},"37126012","huevosabio","Very cool! How much latency does it add?",{"id":166,"by":167,"text":168},"37140999","IanCal","I tried slight modifications from the example pydantic model and it's incredibly slow. Maybe I'm doing something wrong but I've a hefty box and a 3090, an example using gpt-2…",[170,178,186,197],{"value":171,"source":85,"evidence":172},"jsonformer",[173,174],{"id":120,"by":121,"text":122},{"id":175,"by":176,"text":177},"37126329","leetharris","How does this compare in terms of latency, cost, and effectiveness to jsonformer? https:\u002F\u002Fgithub.com\u002F1rgs\u002Fjsonformer",{"value":179,"source":85,"evidence":180},"guidance",[181,182],{"id":120,"by":121,"text":122},{"id":183,"by":184,"text":185},"37125967","2bitencryption","it still blows my mind that OpenAI exposes an API with Functions calling, and yet does not guarantee the model will call your function correctly, in fact, it does not even…",{"value":187,"source":85,"evidence":188},"llama.cpp grammar sampling",[189,193],{"id":190,"by":191,"text":192},"37125368","sneedchucker","Relevant; LLama.cpp implemented grammar-based sampling last month. https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=36819906 https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp\u002Fpull\u002F1773",{"id":194,"by":195,"text":196},"37125552","spott","How does this relate to ggmls bnf sampling?",{"value":198,"source":85,"evidence":199},"TypeChat",[200],{"id":201,"by":202,"text":203},"37125432","Deukhoofd","Looks interesting! How would you say it compares to Microsoft's TypeChat (beyond the obvious Python\u002FTypeScript difference)?…",{"comments":205,"answered":206,"key":207},27,14,[208,211,214],{"id":209,"text":210},"37125691","We can extend our approach to grammar-based sampling, as explained in the paper linked above. Relevant PR: https:\u002F\u002Fgithub.com\u002Fnormal-computing\u002Foutlines\u002Fpull\u002F178 Our method is…",{"id":212,"text":213},"37125712","Thanks! We have extended the approach to grammar-based sampling. We describe the approach in the paper linked above. The following PR is relevant:…",{"id":88,"text":89},{"commenters":216,"max_depth":16,"maker_replies":205,"first_comment_mins":206,"lifespan_hours":217},163,110,[219,223,227,230,233,236,239,241,243,246,248,251,254,256,259,261,264,267,269,272,274,277,281,283,286,289,292,295,297,299,301,304,306,308,311,314,317,320,323,325,328,331,334,338,341,344,347,350,353,356,358,361,364,366,369,371,373,376,378,381,384,387,390,392,396,399,401,403,404,406,410,413,416,420,422,425,428,431,433,434,435,437,439,442,447,449,452,454,458,462,466,469,471,473,476,480,482,486,488,490,492,494,496,498,500,503,505,507,509,511,513,516,518,520,524,528,530,533,536,539,542,545,548,549,551,554,556,558,560,562,564,568,571,573,575,577,580,581,583,586,588,591,593,595,597,600,603,606,608,611,614,616,618,622,625,628,630,633,635,638,640,643,646,648,651,653,655,658,661,663,666,669,672,674,676,678,682,685,689,691,694,696,700,703,707,711,715,719,721,725,727,731,734,736,739,741,745,746,749,753,757,760,764,766,768,770,772,774,776,779,782,784,788,790,792,794,798,802,805,808,811,815,819,823,826,830,834,836,839,841,845,849,851,853,856,859,862,865,869,872,875,877,879,881,883,887,890,892,895,897,898,900,902,906,908,910,914,918,921,923,925,927,929,931,934,937,939,942,944,947,949,952,954,957,960,963,965,967,969,971,973,975,977,979,981,984,986,988,992,996,999,1002,1004,1006,1008,1011,1013,1015,1017,1019],[220,44,45,221,222,44],"37126594","project\u002Fneutral\u002Fidea","activatedgeek",[224,44,44,225,226,44],"37126811","commenter\u002Fneutral\u002Fnone","make3",[228,44,44,225,229,44],"37126938","nabakin",[231,44,44,232,163,44],"37127260","other\u002Fneutral\u002Fnone",[234,44,44,232,235,44],"37128412","dceddia",[237,44,44,225,238,44],"37129595","superkuh",[240,44,44,225,229,44],"37130081",[242,44,45,221,222,44],"37128670",[244,44,45,221,245,44],"37127252","ethbr1",[247,44,45,221,222,44],"37128647",[249,44,44,232,250,44],"37129924","spockz",[252,44,44,232,253,44],"37127435","Havoc",[255,44,44,232,156,44],"37129917",[257,44,44,225,258,44],"37130282","moneywoes",[260,44,44,232,156,44],"37130638",[262,44,44,232,263,44],"37130992","nl",[265,44,44,225,266,44],"37134448","victor106",[268,44,44,225,263,44],"37141203",[270,44,44,232,271,44],"37140638","gsuuon",[273,44,44,232,156,44],"37154424",[275,44,44,232,276,44],"37130885","LakshyAAAgrawal",[278,44,44,279,280,44],"37131227","other\u002Fneutral\u002Fdocs","Roark66",[282,44,44,232,222,44],"37137152",[284,18,44,232,285,44],"37125563","panarky",[287,18,44,232,288,44],"37125700","keiferwiseman",[290,18,44,232,291,44],"37126587","padolsey",[293,18,44,232,294,44],"37127071","gowld",[296,18,44,232,291,44],"37127102",[298,18,44,232,121,44],"37129798",[300,18,44,232,291,44],"37131298",[302,18,44,232,303,44],"37131731","DonHopkins",[305,18,44,232,121,44],"37132028",[307,18,44,225,303,44],"37133044",[309,18,44,232,310,44],"37130347","prempv",[312,18,44,232,313,44],"37126717","MuffinFlavored",[315,18,44,232,316,44],"37127056","padjo",[318,18,44,225,319,44],"37128809","catlifeonmars",[321,18,44,232,322,44],"37129265","antonvs",[324,18,44,225,316,44],"37132328",[326,18,44,225,327,44],"37130648","kristjansson",[329,18,44,232,330,44],"37126751","thumbsup-_-",[332,18,44,232,333,44],"37126896","orasis",[335,18,44,336,337,44],"37126984","other\u002Fcritical\u002Fnone","superasn",[339,18,44,232,340,44],"37126963","phillipcarter",[342,18,44,232,343,44],"37127035","nextaccountic",[345,18,44,346,156,44],"37127042","other\u002Fneutral\u002Fidea",[348,18,44,232,349,44],"37138580","creatonez",[351,18,44,232,352,44],"37127224","caesil",[354,18,44,232,355,44],"37128092","reissbaker",[357,18,44,232,121,44],"37129813",[359,18,44,232,360,44],"37129136","selcuka",[362,18,44,225,363,44],"37130658","ipaddr",[365,18,44,225,360,44],"37130695",[367,18,44,225,368,44],"37134301","tomduncalf",[370,18,44,225,360,44],"37140730",[372,18,44,232,352,44],"37152963",[374,18,44,232,375,44],"37129631","andreygrehov",[377,18,44,232,363,44],"37130717",[379,18,44,232,380,44],"37131505","adamrezich",[382,18,45,221,383,44],"37130792","karmasimida",[385,18,44,225,386,44],"37132041","msp26",[388,18,44,225,389,44],"37132555","vsrinivasan",[98,34,18,391,99,44],"project\u002Fcritical\u002Fidea",[393,34,44,394,395,44],"37131508","commenter\u002Fneutral\u002Fidea","druskacik",[397,34,44,394,398,44],"37133809","newhouseb",[400,34,44,394,167,44],"37134236",[402,34,18,391,99,44],"37135185",[190,45,44,232,191,44],[209,45,44,405,11,18],"project\u002Fpositive\u002Fperformance",[407,45,45,408,409,44],"37126045","project\u002Fneutral\u002Fperformance","popinman322",[411,45,49,405,412,44],"37127072","burke",[414,45,45,221,415,44],"37128086","btwillard",[417,42,49,418,419,44],"37125690","maker\u002Fpositive\u002Fidea","xigency",[212,42,44,421,11,18],"project\u002Fneutral\u002Fnone",[423,42,45,221,424,44],"37126971","Lerc",[426,42,44,232,427,44],"37126190","umvi",[429,42,44,225,430,44],"37127553","winwang",[432,42,45,221,276,44],"37126851",[120,49,18,391,121,44],[88,49,44,405,11,18],[436,49,45,408,412,44],"37127101",[438,49,44,225,11,18],"37134653",[440,49,45,221,441,44],"37137737","mkuchnik",[443,444,49,445,446,44],"37125738",6,"project\u002Fpositive\u002Fidea","J_Shelby_J",[448,444,44,408,11,18],"37125761",[450,444,18,391,451,44],"37126305","behnamoh",[453,444,44,225,11,18],"37126345",[455,444,18,456,457,44],"37126564","project\u002Fcritical\u002Fexecution","dontreact",[459,444,45,460,461,44],"37126770","project\u002Fneutral\u002Fexecution","orlp",[463,444,44,464,465,44],"37126859","commenter\u002Fneutral\u002Fexecution","aassddffasdf",[467,444,44,464,468,44],"37127915","gyy52380",[470,444,44,464,457,44],"37128278",[472,444,44,225,327,44],"37130514",[474,444,45,221,475,44],"37129380","bmc7505",[477,478,44,232,479,44],"37126503",7,"Q6T46nT668w6i3m",[481,478,44,232,415,44],"37126535",[483,484,18,391,485,44],"37131928",8,"YeGoblynQueenne",[487,484,44,394,167,44],"37132093",[489,484,44,394,485,44],"37134690",[491,484,44,394,167,44],"37135000",[493,484,44,394,485,44],"37135205",[495,484,44,394,167,44],"37138029",[497,484,18,391,485,44],"37139667",[499,484,44,221,11,18],"37140169",[501,484,45,502,167,44],"37140964","project\u002Fmixed\u002Fperformance",[504,484,18,391,485,44],"37144475",[506,484,44,225,167,44],"37145706",[508,484,44,225,349,44],"37138673",[510,484,44,221,11,18],"37133005",[512,484,44,225,485,44],"37134701",[514,484,45,221,515,44],"37133064","Silasdev",[517,484,18,391,485,44],"37134725",[102,519,49,445,103,44],9,[521,16,18,522,523,44],"37128463","project\u002Fcritical\u002Fperformance","Scaevolus",[525,526,18,391,527,44],"37125916",11,"Scene_Cast2",[529,526,44,221,11,18],"37126033",[531,526,44,394,532,44],"37126159","Scarblac",[534,526,18,391,535,44],"37126786","haswell",[537,526,45,221,538,44],"37126796","skybrian",[540,526,18,391,541,44],"37128536","pshc",[543,526,44,225,544,44],"37130051","potatoman22",[546,526,45,221,547,44],"37131760","contravariant",[201,39,45,221,202,44],[550,39,44,221,11,18],"37125470",[552,39,45,421,553,44],"37125589","1wheel",[555,39,44,405,11,18],"37125746",[557,39,45,408,544,44],"37130030",[559,39,44,408,11,18],"37133045",[561,39,45,221,184,44],"37126002",[563,39,49,405,415,44],"37126094",[565,566,45,421,567,44],"37125896",13,"Ilasky",[569,566,49,445,570,44],"37125951","londons_explore",[572,566,44,232,567,44],"37126079",[574,566,49,405,567,44],"37126116",[576,566,44,408,11,18],"37126313",[578,566,44,232,579,44],"37126772","thomasfromcdnjs",[109,206,18,391,110,44],[582,206,44,394,144,44],"37126253",[584,206,44,346,585,44],"37126823","chipsrafferty",[587,206,44,225,144,44],"37126848",[589,206,44,225,590,44],"37133150","_flux",[592,206,44,225,144,44],"37134217",[594,206,44,346,538,44],"37127109",[596,206,44,346,424,44],"37127329",[598,206,44,232,599,44],"37128389","bestcoder69",[601,206,44,232,602,44],"37128704","mr_toad",[604,206,45,221,605,44],"37126961","anticrymactic",[607,206,45,221,144,44],"37126995",[609,206,44,225,610,44],"37126482","empath-nirvana",[612,206,44,225,613,44],"37129946","offmycloud",[615,206,49,445,412,44],"37127237",[617,206,45,460,415,44],"37127315",[619,620,18,522,621,44],"37127863",15,"anotherpaulg",[623,620,44,232,624,44],"37128117","infecto",[626,620,44,225,627,44],"37128531","nouri",[629,620,44,232,624,44],"37132383",[631,620,44,232,632,44],"37131068","speedgoose",[634,620,44,232,624,44],"37132369",[636,620,44,232,637,44],"37128315","darkteflon",[155,639,49,445,156,44],16,[641,639,44,232,642,44],"37127292","joshuanapoli",[644,639,44,232,645,44],"37127322","tornato7",[647,639,44,232,156,44],"37127359",[649,639,44,232,650,44],"37127376","M4v3R",[652,639,44,232,544,44],"37127320",[654,639,44,445,11,18],"37135968",[143,656,45,657,144,44],17,"project\u002Fneutral\u002Fdocs",[659,656,44,660,253,44],"37127605","commenter\u002Fneutral\u002Fdocs",[662,656,44,660,144,44],"37127628",[664,656,44,665,11,18],"37127709","project\u002Fpositive\u002Fdocs",[667,656,49,668,140,44],"37128624","maker\u002Fpositive\u002Fdocs",[670,656,45,657,671,44],"37130678","swyx",[673,656,44,225,144,44],"37130764",[675,656,44,660,671,44],"37137643",[677,656,44,225,144,44],"37137678",[679,680,44,232,681,44],"37126884",18,"lettergram",[683,680,44,684,11,18],"37134590","maker\u002Fpositive\u002Fnone",[686,687,45,221,688,44],"37127284",19,"visarga",[690,32,45,460,271,44],"37140417",[692,40,44,346,693,44],"37128280","itissid",[695,40,44,225,485,44],"37135570",[697,698,49,445,699,44],"37125801",22,"thatcherthorn",[701,698,44,702,11,18],"37125814","maker\u002Fneutral\u002Fnone",[704,698,49,705,706,44],"37125847","project\u002Fpositive\u002Fnone","malux85",[708,709,44,232,710,44],"37131359",23,"cztomsik",[712,713,18,391,714,44],"37131850",24,"kevinlu1248",[716,717,45,421,718,44],"37129978",25,"Ycros",[175,720,45,408,176,44],26,[722,720,45,723,724,44],"37126352","project\u002Fneutral\u002Fdesign","bhickey",[726,720,44,460,11,18],"37126388",[728,720,18,729,730,44],"37126669","maker\u002Fcritical\u002Fdocs","Der_Einzige",[732,720,44,733,11,18],"37126743","maker\u002Fneutral\u002Fdocs",[735,205,45,421,253,44],"37125493",[737,205,44,738,11,18],"37125528","project\u002Fpositive\u002Fdesign",[139,740,45,657,140,44],28,[742,743,45,657,744,44],"37126565",29,"btbuildem",[76,743,44,657,11,18],[747,35,45,460,748,44],"37128607","jmcminis",[750,751,18,456,752,44],"37138142",31,"demarq",[754,755,45,657,756,44],"37125920",32,"coding123",[758,755,45,221,759,44],"37127662","odyssey7",[761,762,45,421,763,44],"37129841",33,"AtlasBarfed",[183,765,44,346,184,44],34,[767,765,44,225,121,44],"37126007",[769,765,44,394,184,44],"37126041",[771,765,44,225,121,44],"37126133",[773,765,44,232,451,44],"37126281",[775,765,44,232,398,44],"37126512",[777,765,44,232,778,44],"37128749","reasonabl_human",[780,765,44,232,781,44],"37131193","WiSaGaN",[783,765,18,391,291,44],"37126802",[785,786,45,221,787,44],"37126463",35,"ianbutler",[166,789,18,522,167,44],36,[791,789,44,408,11,18],"37168594",[793,789,45,657,167,44],"37186935",[795,796,45,460,797,44],"37129776",37,"dsrtslnd23",[799,800,44,346,801,44],"37128672",38,"sandkoan",[803,804,18,391,327,44],"37130978",39,[806,804,49,445,807,44],"37131147","TeeWEE",[809,804,45,810,327,44],"37131207","project\u002Fmixed\u002Fidea",[812,813,45,221,814,44],"37130851",40,"aiunboxed",[816,817,45,460,818,44],"37129173",41,"sberens",[820,821,18,456,822,44],"37134451",42,"taeric",[824,821,44,825,11,18],"37168543","project\u002Fpositive\u002Fexecution",[827,828,49,705,829,44],"37164747",43,"Cholical",[831,832,45,221,833,44],"37130789",44,"vlovich123",[835,832,45,221,833,44],"37131028",[837,832,49,445,838,44],"37132728","lexandstuff",[840,832,45,723,833,44],"37134554",[842,843,49,705,844,44],"37128422",45,"oars",[846,847,45,460,848,44],"37130977",46,"calderwoodra",[850,847,44,460,11,18],"37133110",[113,852,18,391,114,44],47,[854,852,49,445,855,44],"37126383","notpushkin",[857,852,45,221,858,44],"37126726","ape4",[860,852,44,232,861,44],"37126846","AtNightWeCode",[863,852,49,445,864,44],"37128151","travisjungroth",[866,867,45,221,868,44],"37133338",48,"rmonvfer",[870,867,44,225,871,44],"37133366","civilitty",[873,874,45,460,409,44],"37126180",49,[876,874,49,445,415,44],"37126196",[132,878,45,421,133,44],50,[880,878,44,702,11,18],"37129923",[151,882,45,421,152,44],51,[884,885,45,408,886,44],"37126699",52,"Kiro",[888,885,45,221,889,44],"37127246","baobabKoodaa",[891,885,45,221,886,44],"37131240",[893,885,44,894,889,44],"37151836","commenter\u002Fneutral\u002Fperformance",[194,896,45,221,195,44],53,[91,896,44,405,11,18],[899,896,45,221,195,44],"37126442",[901,896,44,702,11,18],"37134638",[903,904,18,391,905,44],"37130831",54,"SethTro",[162,907,45,408,163,44],55,[909,907,49,405,415,44],"37126066",[911,912,44,232,913,44],"37134372",56,"jhhgzgft",[915,916,45,221,917,44],"37127827",57,"quickthrower2",[919,916,44,232,920,44],"37128113","mattigames",[922,916,44,232,917,44],"37128203",[924,916,44,232,144,44],"37128396",[926,916,44,232,917,44],"37128586",[928,916,44,232,360,44],"37129024",[930,916,44,232,144,44],"37129803",[932,916,44,232,933,44],"37129324","dilawar",[935,916,18,391,936,44],"37128262","dwattttt",[938,916,18,391,917,44],"37128365",[940,916,44,225,941,44],"37128874","neoncontrails",[943,916,44,394,322,44],"37129229",[945,916,45,221,946,44],"37128603","RyEgswuCsn",[948,916,45,221,319,44],"37128690",[950,916,45,221,951,44],"37128720","MereInterest",[953,916,18,391,946,44],"37146041",[955,916,44,232,956,44],"37128685","OJFord",[958,916,44,232,959,44],"37129039","fenomas",[961,916,44,232,962,44],"37129045","frontier",[964,916,44,232,956,44],"37129257",[966,916,44,232,699,44],"37129309",[968,916,44,232,956,44],"37131554",[970,916,44,232,917,44],"37132332",[972,916,44,232,956,44],"37145554",[974,916,44,232,962,44],"37132192",[976,916,44,232,917,44],"37132304",[978,916,44,232,322,44],"37129240",[980,916,44,232,956,44],"37131679",[982,916,44,232,983,44],"37129386","pavs",[985,916,44,232,956,44],"37131677",[987,916,44,232,917,44],"37132345",[989,990,18,522,991,44],"37130812",58,"malft",[993,994,44,232,995,44],"37126524",59,"rckrd",[124,997,18,998,125,44],60,"project\u002Fcritical\u002Fdocs",[1000,997,44,660,1001,44],"37128508","verdverm",[1003,997,44,660,125,44],"37128754",[1005,997,44,660,590,44],"37131234",[1007,997,44,660,125,44],"37132235",[1009,997,44,1010,724,44],"37128775","commenter\u002Fcritical\u002Fdocs",[1012,997,44,660,125,44],"37129396",[1014,997,44,660,724,44],"37129504",[1016,997,44,660,125,44],"37132338",[1018,997,18,391,724,44],"37132591",[1020,1021,45,221,1022,44],"37130724",61,"faangiq",[],[1025,1030,1035,1039,1044,1049],{"id":1026,"name":1027,"points":1028,"category":1029},"37119942","Little Rat",555,"security_privacy",{"id":1031,"name":1032,"points":1033,"category":1034},"37083309","OFRAK Tetris",472,"games",{"id":1036,"name":1037,"points":1038,"category":20},"37128293","AI-town",429,{"id":1040,"name":1041,"points":1042,"category":1043},"37114141","learndb-py",371,"learning_science",{"id":1045,"name":1046,"points":1047,"category":1048},"37075730","Applite",280,"dev_tools",{"id":1050,"name":1051,"points":1052,"category":20},"37148210","LlamaGPT",225,false,"v2",{"id":1056,"name":5,"line":6,"ai":1053,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":1057,"top":18,"kw":1058,"maker":11,"domain":10,"tier":19,"attempts":44,"strip":1059,"url":9,"mix":1060,"praise":84,"objection":95,"sub":21},37125118,-0.11,[24,25,26,27,28],"3300000314221111351335434220234443311011",[32,33,34,35],1794036640079]