[{"data":1,"prerenderedAt":150},["ShallowReactive",2],{"project-47143717":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":31,"aspects":33,"strip":37,"post_text":38,"what":39,"said":53,"maker_in_thread":88,"shape":92,"grid":97,"attempts":109,"same_week":114,"maker_shows":15,"maker_hidden":143,"reader_version":144,"card":145},"47143717","Recursive Pattern Pathfinder","Recursively apply patterns for pathfinding","title","Show HN: Recursively apply patterns for pathfinding","https:\u002F\u002Fpattern-pathfinder.vercel.app\u002F?fixtureId=%7B%22path%22%3A%22site%2Fexamples%2F_intro.fixture.tsx%22%7D","pattern-pathfinder.vercel.app","seveibar",1771969871,2026,26,5,1753,4366,41,"shown","hardware","pcb autorouting","web_app",[24,25,26,27],"autorouting","pcb routing","pathfinding","circuit board design","quiet",null,{"positive":31,"neutral":32,"mixed":32,"critical":32},2,0,{"docs":34,"idea":36},{"positive":35,"critical":32},1,{"positive":35,"critical":32},[15,15,32,32,32],"I've been begrudgingly working on autorouters for 2 years, looking for new techniques or modern methods that might allow AI to create circuit boards.\n\nOne of the biggest problems in my view for training an AI to do autorouting is the traditional grid-based representation of autorouting problems which challenges spatial understanding. But we know that vision models are very good at classifying, so I wondered if we could train a model to output a path as a classification. But then how do you represent the path? This lead me down the track of trying to build an autorouter that represented paths a",{"problem":40,"audience":29,"pricing":29,"motivation":46,"time_to_build":29,"stack":50,"openness":51,"stage":52,"team_size":51},{"value":41,"source":42,"evidence":43},"Autorouting circuit board traces is hard for AI because grid-based representations challenge spatial understanding.","maker",[44],{"id":45},"post",{"value":47,"source":42,"evidence":48},"Wants to train AI to autoroute circuit boards by treating paths as classifiable patterns.",[49],{"id":45},[],"unknown","prototype",{"praise":54,"objections":63,"requests":68,"questions":73,"alternatives":78},[55],{"value":56,"source":57,"evidence":58},"Commenters find the project cool and a sweet application of AI.","commenter",[59],{"id":60,"by":61,"text":62},"47145035","dvt","This is super cool, any papers I can read on autorouting? I occasionally see inefficiencies[1][2] so I suspect this isn't exactly a free lunch, and I'd like to read something a…",[64],{"value":65,"source":57,"evidence":66},"Suspects autorouting approach has inefficiencies and is not a free lunch.",[67],{"id":60,"by":61,"text":62},[69],{"value":70,"source":57,"evidence":71},"Requests papers on autorouting, especially critical ones.",[72],{"id":60,"by":61,"text":62},[74],{"value":75,"source":57,"evidence":76},"Which papers on autorouting should be read?",[77],{"id":60,"by":61,"text":62},[79],{"value":80,"source":42,"evidence":81},"OpenROAD VLSI algorithms and game-dev pathfinding techniques such as navmeshes and Polyanya.",[82,85],{"id":83,"by":11,"text":84},"47146590","Despite what electrical engineers would claim, I think it's very under-studied under a modern lens. When people ask for good places to get started I usually tell them to just…",{"id":86,"by":11,"text":87},"47148121","Game developers do bake navmeshes that's true, but it's not the only technique, for example they've also come up with Polyana or \"any-angle pathfinding\"…",{"comments":31,"answered":35,"key":89},[90,91],{"id":83,"text":84},{"id":86,"text":87},{"commenters":93,"max_depth":94,"maker_replies":31,"first_comment_mins":95,"lifespan_hours":96},3,4,52,9,[98,102,104,106,108],[99,32,15,100,101,32],"47144416","maker\u002Fpositive\u002Fdocs","sublinear",[60,35,15,103,61,32],"project\u002Fpositive\u002Fidea",[83,35,32,105,11,35],"commenter\u002Fneutral\u002Fidea",[107,35,32,105,61,32],"47146904",[86,35,32,105,11,35],[110,113],{"id":111,"t":112,"points":35,"comments":32},"42707004",1736911871,{"id":4,"t":12,"points":14,"comments":15},[115,120,125,130,134,139],{"id":116,"name":117,"points":118,"category":119},"47075124","Micasa",657,"productivity",{"id":121,"name":122,"points":123,"category":124},"47114530","CIA World Factbook Archive",496,"learning_science",{"id":126,"name":127,"points":128,"category":129},"47104667","ntransformer",395,"ai",{"id":131,"name":132,"points":133,"category":129},"47131225","Steerling-8B",328,{"id":135,"name":136,"points":137,"category":138},"47123631","PgDog",326,"infrastructure",{"id":140,"name":141,"points":142,"category":129},"47143755","Moonshine Open-Weights STT models",316,false,"v2",{"id":146,"name":5,"line":6,"ai":143,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":147,"maker":11,"domain":10,"tier":19,"attempts":31,"strip":148,"url":9,"mix":149,"praise":56,"objection":65,"sub":21},47143717,[24,25,26,27],"55000",[31,32,32,32],1793991145478]