[{"data":1,"prerenderedAt":743},["ShallowReactive",2],{"project-35073603":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":43,"post_text":46,"what":47,"said":102,"maker_in_thread":210,"shape":221,"grid":225,"attempts":703,"same_week":704,"maker_shows":31,"maker_hidden":735,"reader_version":736,"card":737},"35073603","Braggoscope","BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT","title","Show HN: BBC “In Our Time”, categorised by Dewey Decimal, heavy lifting by GPT","https:\u002F\u002Fgenmon.github.io\u002Fbraggoscope\u002F","genmon.github.io","genmon",1678303694,2023,688,171,24,3109,1,"legend","learning_science","podcast archive","web_app",[24,25,21,26,27],"in our time","dewey decimal","gpt-3","bbc podcast","mixed",0.221,{"positive":16,"neutral":16,"mixed":31,"critical":32},2,12,62,{"idea":35,"design":38,"execution":40,"docs":42},{"positive":36,"critical":37},13,5,{"positive":18,"critical":39},0,{"positive":39,"critical":41},6,{"positive":18,"critical":39},[37,39,39,39,39,39,44,44,37,37,44,44,44,39,39,44,44,44,44,45,44,39,39,37,44,39,39,39,44,44,18,45,37,37,18,31,37,45,37,45],3,4,"I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs.\n\nIn Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised.\n\nSo here are the episodes sorted by library code. It's fun to explore.\n\nWeb scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition.\n\nAt the same time I",{"problem":48,"audience":54,"pricing":63,"motivation":64,"time_to_build":63,"stack":68,"openness":99,"stage":100,"team_size":101},{"value":49,"source":50,"evidence":51},"In Our Time has nearly 1,000 episodes that are poorly organised, making topics hard to browse","maker",[52],{"id":53},"post",{"value":55,"source":56,"evidence":57},"Listeners of the BBC In Our Time podcast","inferred",[58,59],{"id":53},{"id":60,"by":61,"text":62},"35074386","astroalex","I love this project!! Ever since my partner and I discovered In Our Time a few years back, it’s been our go-to podcast to listen to together. Part of the allure is that the…",null,{"value":65,"source":50,"evidence":66},"Make the In Our Time archive easier to explore and learn from, and test LLM use for data extraction",[67],{"id":53},[69,76,85,91,95],{"value":70,"source":50,"evidence":71},"GPT-3",[72,73],{"id":53},{"id":74,"by":11,"text":75},"35073875","There's more on the About page but in summary: extracts the synopsis, guests (name, affiliation), and reading list (title, author, publisher, year) as structured data. Not…",{"value":77,"source":50,"evidence":78},"OpenAI embeddings",[79,82],{"id":80,"by":11,"text":81},"35074059","Some unlinked features... If you put the Dewey division in the URL, the directory auto-opens. e.g. here are episodes about prehistoric life (my current jumping-off point)…",{"id":83,"by":11,"text":84},"35074527","Colour is the 3rd component -- I wanted to see the difference between overlapping episodes. As for the 3D plot... here you go!…",{"value":86,"source":50,"evidence":87},"SQLite",[88],{"id":89,"by":11,"text":90},"35075368","I think Angie Hobbs will take it! Looks like she is referred to with a few different names in the episode notes and I’ll need to merge them manually (will be 25 appearances) (btw…",{"value":92,"source":50,"evidence":93},"Datasette",[94],{"id":89,"by":11,"text":90},{"value":96,"source":50,"evidence":97},"Python",[98],{"id":83,"by":11,"text":84},"unknown","launched","solo",{"praise":103,"objections":132,"requests":159,"questions":178,"alternatives":198},[104,117],{"value":105,"source":106,"evidence":107},"Useful way to browse and discover episodes","commenter",[108,112,113],{"id":109,"by":110,"text":111},"35073714","valgaze","This is a really interesting use-case Applying \"transformations\" or classifying data in this way without having to setup a lot of detail-work seems like a real…",{"id":60,"by":61,"text":62},{"id":114,"by":115,"text":116},"35082126","joshspankit","This is amazing, and exactly the kind of thing I’ve been hoping for to help us find the gems in the endless stream of excellent content. What would it take to go deeper on this…",{"value":118,"source":106,"evidence":119},"Impressive use of LLMs for structured data extraction",[120,124,128],{"id":121,"by":122,"text":123},"35080916","ourmandave","Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript…",{"id":125,"by":126,"text":127},"35075524","cheschire","No longer does Tony the Pony need to parse XHTML with regex. Who knew GPTs would be the actual solution?",{"id":129,"by":130,"text":131},"35078288","devharshit","This is actually amazing",[133,152],{"value":134,"source":106,"evidence":135},"Some Dewey classifications are wrong or questionable",[136,140,144,148],{"id":137,"by":138,"text":139},"35073924","aardvark179","I see several very dubious classifications. Shouldn’t the great stink be under civil engineering rather than agriculture, and why is Plato’s Atlantis under computer science?",{"id":141,"by":142,"text":143},"35076033","SomewhatLikely","I'm not sure this one about sewage is correctly classified. It's in agriculture, presumably because it mentions fertilizing fields. It probably fits better under engineering.…",{"id":145,"by":146,"text":147},"35076477","arsome","Tea under Economics and coffee under Technology > Home and family management... some... interesting decisions in here.",{"id":149,"by":150,"text":151},"35077944","lisasays","At the same time I asked for a Dewey classification... and it worked. May I ask - how do you know exactly? Specifically - with what level of accuracy? And how is it assessed? At…",{"value":153,"source":106,"evidence":154},"Episode titles wrong for some subtitled episodes",[155],{"id":156,"by":157,"text":158},"35080749","jgtrosh","Some episodes that have subtitles are titled incorrectly (only using the subtitle). For example, this episode [1] is the first of a pair of episodes called The Written World, but…",[160,171],{"value":161,"source":106,"evidence":162},"Semantic search or transcription with Whisper",[163,167],{"id":164,"by":165,"text":166},"35073883","specproc","I love In Our Time, a real BBC gem. I've been meaning to pull all the audio for a while and this has inspired me. A fun thing to do would be to pass through Whisper, a great…",{"id":168,"by":169,"text":170},"35074899","maccaw","Love it - also a huge fan of In our Time. V2 would be: - Transcribe through Whisper - Semantic search",{"value":172,"source":106,"evidence":173},"Alphabetical topic list",[174],{"id":175,"by":176,"text":177},"35074721","jccalhoun","It is an interesting approach and I appreciate it. However, an alphabetical list would be more useful for me when I am interested in topics and might not know where they are…",[179,190],{"value":180,"source":106,"evidence":181},"What prompt was used",[182,186],{"id":183,"by":184,"text":185},"35073745","PaulHoule","What's the prompt?",{"id":187,"by":188,"text":189},"35076695","nextaccountic","> Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript…",{"value":191,"source":106,"evidence":192},"How accuracy was measured and how errors are fixed",[193,194],{"id":149,"by":150,"text":151},{"id":195,"by":196,"text":197},"35081380","OOPMan","How perfect is almost perfect? How do you correct errors?",[199,203],{"value":200,"source":106,"evidence":201},"Wikipedia-based manual categorisation by a partner's archive",[202],{"id":60,"by":61,"text":62},{"value":204,"source":106,"evidence":205},"Weekend Collection catalog",[206],{"id":207,"by":208,"text":209},"35074604","theodorewiles","I emailed you but did something similar and posted to Show HN a while back - https:\u002F\u002Fweekend-collection.s3.amazonaws.com\u002FCatalog+-+Feb+17.html",{"comments":211,"answered":212,"key":213},22,8,[214,215,218],{"id":80,"text":81},{"id":216,"text":217},"35074551","It turns out that \"closeness\" is usually hard to visualise\u002Fexplore when you're dealing with a 1,000-dimensional space... and PCA has the failures mentioned above. It's weird --…",{"id":219,"text":220},"35074819","Excellent, new to me and I'll give it a go, thanks! I gravitate to PCA for terrible reasons (undergrad so it's what I think of first) and like you say, it's beguiling yet…",{"commenters":222,"max_depth":41,"maker_replies":211,"first_comment_mins":223,"lifespan_hours":224},114,9,84,[226,230,234,238,242,245,248,251,254,257,259,263,266,270,272,275,278,281,283,286,288,291,293,296,298,301,304,307,309,313,315,319,320,323,325,328,331,332,334,337,339,342,344,348,350,353,355,358,362,363,366,368,371,375,378,380,383,386,389,392,395,398,400,403,405,408,410,414,415,417,420,423,426,428,431,434,437,440,443,445,447,449,452,455,456,458,462,464,466,469,471,473,475,478,481,483,485,488,490,492,494,496,499,501,504,507,510,514,517,519,522,525,527,530,533,536,539,542,545,547,549,553,558,561,563,566,570,572,574,576,580,582,585,587,588,592,593,595,598,603,607,611,616,618,621,625,629,632,635,638,641,645,648,650,654,658,660,664,668,671,675,677,679,681,683,686,688,691,693,697,699],[227,39,37,228,229,39],"35075193","project\u002Fpositive\u002Fidea","mattlondon",[231,39,39,232,233,39],"35076038","other\u002Fneutral\u002Fnone","ketzo",[235,39,39,236,237,39],"35076189","commenter\u002Fcritical\u002Fidea","chaxor",[239,39,39,240,241,39],"35081937","commenter\u002Fneutral\u002Fidea","seagullriffic",[243,39,39,232,244,39],"35076192","v7n",[246,39,39,232,247,39],"35076292","TaylorAlexander",[249,39,39,232,250,39],"35079500","martyvis",[252,39,39,232,253,39],"35076689","fnordpiglet",[255,39,39,232,256,39],"35080235","ewalk153",[258,39,39,232,253,39],"35080955",[260,39,39,261,262,39],"35077815","other\u002Fneutral\u002Fidea","samplatt",[264,39,39,232,265,39],"35078951","brutusborn",[267,39,39,268,269,39],"35080466","commenter\u002Fneutral\u002Fnone","yarbas89",[271,39,39,268,265,39],"35081203",[273,39,39,261,274,39],"35077119","nl",[276,39,39,232,277,39],"35078009","chrisweekly",[279,39,39,232,280,39],"35078326","EZ-Cheeze",[282,39,39,232,280,39],"35078321",[284,39,39,261,285,39],"35078680","basch",[287,39,39,232,280,39],"35078813",[289,39,39,232,290,39],"35078888","nico",[292,39,39,232,285,39],"35081525",[294,39,39,232,295,39],"35080109","sho_hn",[297,39,39,261,285,39],"35078631",[299,39,39,232,300,39],"35079482","novaRom",[302,39,39,303,196,39],"35081458","commenter\u002Fcritical\u002Fnone",[305,39,39,261,306,39],"35089224","JRagone",[80,18,39,308,11,18],"project\u002Fpositive\u002Fdesign",[310,18,44,311,312,39],"35074392","project\u002Fneutral\u002Fidea","CrypticShift",[216,18,39,314,11,18],"maker\u002Fneutral\u002Fnone",[316,18,44,317,318,39],"35074726","project\u002Fneutral\u002Fdesign","gwern",[219,18,39,314,11,18],[321,18,44,317,322,39],"35074791","pigscantfly",[324,18,44,317,274,39],"35078268",[326,18,39,232,327,39],"35082297","PeterisP",[329,18,44,317,330,39],"35074396","p0pcult",[83,18,39,308,11,18],[333,18,37,308,330,39],"35075180",[335,18,37,228,336,39],"35075253","flir",[338,18,39,261,253,39],"35076755",[340,18,39,232,341,39],"35077399","chezelenkoooo",[343,18,39,232,274,39],"35078255",[345,18,39,346,347,39],"35078345","other\u002Fcritical\u002Fnone","snowe2010",[349,18,39,232,253,39],"35078519",[351,18,39,346,352,39],"35080742","amiga386",[354,18,39,303,253,39],"35080952",[356,18,44,317,357,39],"35076927","Tarq0n",[359,18,18,360,361,39],"35079472","project\u002Fcritical\u002Fnone","shellac",[60,31,37,228,61,39],[364,31,39,365,11,18],"35074567","other\u002Fpositive\u002Fdesign",[367,31,39,232,61,39],"35076069",[369,31,44,311,370,39],"35074746","zeristor",[372,31,39,373,374,39],"35074919","other\u002Fpositive\u002Fidea","bscphil",[376,44,39,232,377,39],"35074910","DC-3",[379,44,39,232,11,18],"35075159",[381,44,39,232,382,39],"35075763","yung_steezy",[384,44,39,232,385,39],"35075872","dendrite9",[387,44,39,232,388,39],"35076631","martinpw",[390,44,39,232,391,39],"35076299","aslfjiasf",[393,44,39,346,394,39],"35078751","rosetremiere",[396,44,39,268,397,39],"35078782","petesergeant",[399,44,39,268,394,39],"35079378",[401,44,39,268,402,39],"35080167","mellosouls",[404,44,39,268,377,39],"35079587",[406,44,39,232,407,39],"35079735","gadders",[409,44,39,268,394,39],"35079930",[411,45,44,412,413,39],"35075306","project\u002Fneutral\u002Fnone","simonw",[89,45,39,314,11,18],[416,45,44,412,413,39],"35075490",[418,45,39,232,419,39],"35075530","I_complete_me",[421,45,39,232,422,39],"35075696","rwmj",[424,45,39,232,425,39],"35076295","FearNotDaniel",[187,37,44,427,188,39],"project\u002Fneutral\u002Fexecution",[429,37,44,427,430,39],"35077523","kwerk",[432,37,44,427,433,39],"35077857","malborodog",[435,37,39,436,11,18],"35098069","maker\u002Fpositive\u002Fexecution",[438,37,37,439,433,39],"35113917","maker\u002Fpositive\u002Fnone",[441,37,39,442,11,18],"35098011","maker\u002Fneutral\u002Fdocs",[137,41,18,444,138,39],"project\u002Fcritical\u002Fexecution",[446,41,39,427,11,18],"35073958",[448,41,44,311,208,39],"35076197",[450,41,44,412,451,39],"35074032","once_inc",[149,453,44,454,150,39],7,"project\u002Fmixed\u002Fexecution",[164,212,37,228,165,39],[457,212,39,311,11,18],"35073907",[459,212,44,460,461,39],"35074084","project\u002Fneutral\u002Fdocs","taberiand",[463,212,39,439,11,18],"35074588",[465,212,44,460,413,39],"35075196",[467,212,39,232,468,39],"35074729","coder543",[470,212,39,232,413,39],"35075177",[472,212,39,232,468,39],"35075269",[474,212,39,232,413,39],"35075503",[476,212,39,232,477,39],"35078195","akras14",[479,223,39,232,480,39],"35074747","jack_riminton",[482,223,39,232,11,18],"35074779",[484,223,39,232,480,39],"35075960",[486,223,39,232,487,39],"35077017","gerdesj",[207,489,39,232,208,39],10,[491,489,39,268,11,18],"35074979",[493,489,39,268,208,39],"35076207",[109,495,37,228,110,39],11,[497,495,37,228,498,39],"35074054","lerchmo",[500,495,39,232,11,18],"35074635",[502,32,44,311,503,39],"35075400","donut",[505,32,39,506,11,18],"35075531","project\u002Fmixed\u002Fidea",[508,36,39,232,509,39],"35079489","thom",[511,512,39,232,513,39],"35073739",14,"haolez",[515,512,39,232,516,39],"35073760","LeoPanthera",[518,512,39,232,110,39],"35073789",[520,512,39,232,521,39],"35074221","gwillen",[523,512,39,232,524,39],"35076012","Jensson",[526,512,39,311,11,18],"35073793",[528,512,39,232,529,39],"35073845","acchow",[531,512,39,232,532,39],"35073955","messe",[534,512,39,232,535,39],"35092136","igravious",[537,512,39,232,538,39],"35073852","tedsanders",[540,512,39,232,541,39],"35082787","minkzilla",[543,512,39,232,544,39],"35082949","ChatGTP",[546,512,39,232,541,39],"35102492",[548,512,39,232,169,39],"35074884",[550,551,37,439,552,39],"35080301",15,"Southworth",[554,555,18,556,557,39],"35079569",16,"project\u002Fcritical\u002Fidea","DeathArrow",[559,555,39,268,560,39],"35079780","thewarrior",[562,555,39,268,557,39],"35079842",[175,564,44,565,176,39],17,"project\u002Fmixed\u002Fdesign",[567,568,39,232,569,39],"35075406",18,"vidro3",[571,568,39,232,11,18],"35075506",[573,568,39,232,336,39],"35076170",[156,575,18,444,157,39],19,[577,578,39,232,579,39],"35077269",20,"totetsu",[141,581,18,444,142,39],21,[583,211,39,232,584,39],"35079098","lysecret",[121,586,37,228,122,39],23,[114,16,37,228,115,39],[589,590,18,556,591,39],"35073812",25,"dvt",[74,590,39,314,11,18],[594,590,37,439,433,39],"35077939",[596,590,44,412,597,39],"35074249","sorokod",[599,600,37,601,602,39],"35074156",26,"project\u002Fpositive\u002Fnone","boringg",[604,605,37,228,606,39],"35080080",27,"corobo",[608,609,44,311,610,39],"35076521",28,"ada1981",[612,613,44,614,615,39],"35081308",29,"maker\u002Fneutral\u002Fexecution","Janymos",[617,613,39,614,11,18],"35098158",[619,620,39,232,584,39],"35081652",30,[622,623,37,601,624,39],"35073927",31,"jgrahamc",[626,627,18,556,628,39],"35079145",32,"coob",[630,627,18,556,631,39],"35079174","ImaCake",[633,627,39,232,634,39],"35079181","etewiah",[636,627,18,444,637,39],"35079437","kzrdude",[639,627,18,556,640,39],"35080072","davidy123",[642,643,37,228,644,39],"35077992",33,"SnoJohn",[646,647,39,232,407,39],"35079699",34,[145,649,18,444,146,39],35,[651,652,44,311,653,39],"35081071",36,"mymythisisthis",[655,656,37,601,657,39],"35076330",37,"viburnum",[125,659,37,228,126,39],38,[661,662,37,228,663,39],"35075736",39,"haunter",[665,666,39,232,667,39],"35074898",40,"EamonnMR",[669,666,39,232,670,39],"35081245","open-source-ux",[672,673,44,412,674,39],"35076932",41,"megablast",[168,676,37,228,169,39],42,[183,678,44,460,184,39],43,[680,678,39,268,110,39],"35073816",[682,678,39,442,11,18],"35073824",[684,678,37,685,498,39],"35074061","maker\u002Fpositive\u002Fdocs",[687,678,39,314,11,18],"35074661",[689,678,18,444,690,39],"35104401","noahbrier",[195,692,44,614,196,39],44,[694,695,37,601,696,39],"35117830",45,"gnutmal",[129,698,37,601,130,39],46,[700,701,37,601,702,39],"35078968",47,"dirtyid",[],[705,710,715,720,725,730],{"id":706,"name":707,"points":708,"category":709},"35032506","Lander",564,"games",{"id":711,"name":712,"points":713,"category":714},"35026902","Llama-dl",343,"ai",{"id":716,"name":717,"points":718,"category":719},"35055308","NESFab",298,"languages",{"id":721,"name":722,"points":723,"category":724},"35042316","UJRPC",290,"infrastructure",{"id":726,"name":727,"points":728,"category":729},"34999774","Mathesar",281,"data",{"id":731,"name":732,"points":733,"category":734},"35071755","CodeGPT.nvim",228,"dev_tools",false,"v2",{"id":738,"name":5,"line":6,"ai":735,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":739,"top":18,"kw":740,"maker":11,"domain":10,"tier":19,"attempts":39,"strip":741,"url":9,"mix":742,"praise":105,"objection":134,"sub":21},35073603,0.22,[24,25,21,26,27],"5000003355333003333430053000331455125454",[16,16,31,32],1794036632286]