[{"data":1,"prerenderedAt":524},["ShallowReactive",2],{"project-36882146":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":35,"aspects":36,"strip":47,"post_text":49,"what":50,"said":94,"maker_in_thread":221,"shape":234,"grid":239,"attempts":487,"same_week":488,"maker_shows":320,"maker_hidden":516,"reader_version":517,"card":518},"36882146","Continue","Open-source coding autopilot","title","Show HN: Continue – Open-source coding autopilot","https:\u002F\u002Fgithub.com\u002Fcontinuedev\u002Fcontinue","github.com","sestinj",1690394669,2023,298,103,147,3109,5,"legend","dev_tools","ai coding assistant","desktop_app",[24,25,26,27],"llm coding assistant","vs code extension","open source copilot","local llm","debated",-0.084,{"positive":31,"neutral":32,"mixed":33,"critical":34},11,20,1,12,44,{"idea":37,"design":39,"execution":40,"privacy":41,"performance":43,"docs":45,"pricing":46},{"positive":38,"critical":38},2,{"positive":38,"critical":33},{"positive":33,"critical":38},{"positive":38,"critical":42},6,{"positive":44,"critical":44},0,{"positive":44,"critical":44},{"positive":44,"critical":33},[48,48,44,44,44,48,48,33,33,33,48,48,33,18,44,33,18,44,44,48,33,48,18,48,44,33,18,48,48,18,48,48,48,33,18,48,48,48,48,48],3,"Hi HN, we’re Nate and Ty, co-founders of Continue, an open-source autopilot for software development built to be deeply customizable and continuously learn from development data. It consists of an extended language server and (to start) a VS Code extension.\n\nOur GitHub is https:\u002F\u002Fgithub.com\u002Fcontinuedev\u002Fcontinue. You can watch a demo of Continue and download the extension at https:\u002F\u002Fcontinue.dev\n\n— — —\n\nA growing number of developers are replacing Google + Stack Overflow with Large Language Models (LLMs) as their primary approach to get help, similar to how developers previously replaced refere",{"problem":51,"audience":57,"pricing":61,"motivation":70,"time_to_build":74,"stack":75,"openness":91,"stage":92,"team_size":93},{"value":52,"source":53,"evidence":54},"Developers copy\u002Fpaste between ChatGPT and the editor and lack transparency over the context LLM coding tools use","maker",[55],{"id":56},"post",{"value":58,"source":53,"evidence":59},"Software developers using LLMs for coding help",[60],{"id":56},{"value":62,"source":53,"evidence":63},"Free with 250 free GPT-4 requests; plans to sell a paid development data engine to organizations",[64,67],{"id":65,"by":11,"text":66},"36886324","We wanted to make it as easy as possible for people to try Continue, so we allow 250 free requests. These use gpt4. If you plug in your own API key in VS Code settings, it will…",{"id":68,"by":11,"text":69},"36894967","Great question! We plan to make money by helping organizations continuously collect, analyze, and train on their development data. This will let them a) understand ROI of using…",{"value":71,"source":53,"evidence":72},"Give developers transparency, hackability and control over LLM tools and their own development data",[73],{"id":56},null,[76,80,87],{"value":77,"source":53,"evidence":78},"VS Code extension",[79],{"id":56},{"value":81,"source":82,"evidence":83},"Python server","commenter",[84],{"id":85,"by":11,"text":86},"36886983","I'm not aware of any reason we would be connecting to windows.net. I would be surprised if VS Code did not already have access to Desktop \u002F Documents \u002F etc. but if this is the…",{"value":88,"source":53,"evidence":89},"Meilisearch",[90],{"id":85,"by":11,"text":86},"open_source","launched","team",{"praise":95,"objections":118,"requests":148,"questions":178,"alternatives":193},[96,107],{"value":97,"source":82,"evidence":98},"Clean UX that avoids copy\u002Fpaste and gives precise highlight-based context",[99,103],{"id":100,"by":101,"text":102},"36885989","dimal","This looks great! I’ve been pretty underwhelmed with the UX of the other VS Code extensions, for just the reasons you list. This looks a lot like how I imagined an AI extension…",{"id":104,"by":105,"text":106},"36885661","jierlich","Been using Continue for a few weeks in combination with GH co-pilot. Overall it's been a solid experience. After a few days of adjusting, it's become my go to because I don't…",{"value":108,"source":82,"evidence":109},"Open source with support for local and open models",[110,114],{"id":111,"by":112,"text":113},"36886021","satvikpendem","Looks like this is similar to GitHub Copilot Chat [0], just open source right? I like that you're supporting open models as well rather than just ChatGPT. Is there a way for your…",{"id":115,"by":116,"text":117},"36901183","whoisjuan","Hey. I gave it a try to Continue and I think this is going in the right direction at least for me. I guess opinions on how this should work are subjective. But I do really like…",[119,130,141],{"value":120,"source":82,"evidence":121},"Initially sent data to telemetry and third-party services without clear consent, since removed",[122,126],{"id":123,"by":124,"text":125},"36886121","krono","A cursory look through the source reveals the presence of three different telemetry suites of which only Posthog looks to be properly documented. I could have overlooked it, but…",{"id":127,"by":128,"text":129},"36889195","smcleod","Looks like it's trying to send my data to \"meilisearch\" without asking me :\u002F",{"value":131,"source":82,"evidence":132},"Unclear which model and key are used and what the free tier covers",[133,137],{"id":134,"by":135,"text":136},"36886209","rodrigodlu","Hey! Thanks for this tool. I was testing and paying copilot, including the new chat integrated tool, but I feel your work flow proposal is more compelling. That said, I'm not…",{"id":138,"by":139,"text":140},"36889078","jenadine","I don't find this clear in the website what LLM it is really using. Is it sending my code and queries over the internet? Or can it use a local language model?",{"value":142,"source":82,"evidence":143},"Monetization via an external API could be risky",[144],{"id":145,"by":146,"text":147},"36889889","jossclimb","How are you going to monetize this? I would be very nervous building a business around an extension calling someone elses API. You only have to look at the drama that played out…",[149,160,167],{"value":150,"source":82,"evidence":151},"Support for JetBrains IDEs",[152,156],{"id":153,"by":154,"text":155},"36885948","nraf","Any plans for supporting Jetbrains IDEs?",{"id":157,"by":158,"text":159},"36893616","mijoharas","Are you planning to support any other editors any time soon?",{"value":161,"source":82,"evidence":162},"Automatic related-definition context from the language server",[163],{"id":164,"by":165,"text":166},"36886291","milani","In my experience working with GPT4, if I give enough context on types, other functions definitions and the libraries I use, I get very accurate results. But it is a tedious task…",{"value":168,"source":82,"evidence":169},"Read terminal output and web pages as context",[170,174],{"id":171,"by":172,"text":173},"36890819","pax","Is there any LLM based coding assistant than can read from terminal, thus catching error output?",{"id":175,"by":176,"text":177},"36887991","FloatArtifact","Thank you for supporting an open source ecosystem. A couple of thoughts. 1. It would be nice if we could ingest external resources like web pages. 2. Deep integration with the…",[179,186],{"value":180,"source":82,"evidence":181},"Which local models perform well",[182],{"id":183,"by":184,"text":185},"36886937","simonw","\"Continue works with any LLM, including local models using ggml\" Which of the local models have you seen the best results with? UPDATE: Found a note here…",{"value":187,"source":82,"evidence":188},"Whether it works without GPT-4 for cost reasons",[189],{"id":190,"by":191,"text":192},"36890695","AstraZenecat","does this require gpt-4? I can't afford such a luxury sadly.",[194,201,208,215],{"value":195,"source":82,"evidence":196},"GitHub Copilot and Copilot Chat",[197,200],{"id":198,"by":11,"text":199},"36885991","Focusing on VS Code for at least the next few weeks, but we've planned from the start! You can read more here (https:\u002F\u002Fcontinue.dev\u002Fdocs\u002Fhow-continue-works), but the Continue…",{"id":111,"by":112,"text":113},{"value":202,"source":82,"evidence":203},"Rubberduck VS Code extension",[204],{"id":205,"by":206,"text":207},"36887234","extr","Check out the Rubberduck Extension [1] for VS Code. It's not super well publicized but I've actually found it basically hits a perfect middle ground between copilot and…",{"value":209,"source":82,"evidence":210},"Aider",[211],{"id":212,"by":213,"text":214},"36887009","anotherpaulg","This looks really interesting. Have you spent much time investigating how to provide code context to the LLM without needing to manually highlight all the relevant code? That’s…",{"value":216,"source":82,"evidence":217},"Cody",[218],{"id":219,"by":116,"text":220},"36887135","Why is nobody in this space making good gains on UX? I have tried almost every co-pilot solution, including GitHub Co-Pilot with Chat and Labs, Cody, and a few random extensions.…",{"comments":222,"answered":223,"key":224},31,17,[225,228,231],{"id":226,"text":227},"36886378","This is very near on the roadmap, and we agree it will be awesome! As of now, if there are collections of definitions that you frequently reference, you could save them in the…",{"id":229,"text":230},"36888682","Couldn't agree more—it's worth the extra effort to know exactly what enters the prompt. But control isn't mutually exclusive with removing the need to copy\u002Fpaste. Continue lets…",{"id":232,"text":233},"36887580","We have something similar in our plans. While the LSP doesn't directly offer all of the APIs we need, we want to be an \"extended LSP\", and integrate an LSP as part of the…",{"commenters":235,"max_depth":236,"maker_replies":222,"first_comment_mins":237,"lifespan_hours":238},45,7,229,95,[240,242,243,247,249,252,255,258,261,263,265,268,271,273,276,279,281,283,285,287,291,293,296,298,300,303,306,309,311,313,317,319,322,324,327,330,333,335,339,343,346,347,349,352,354,357,360,363,364,366,367,370,373,375,377,380,383,386,389,391,394,396,398,401,403,405,408,410,412,413,415,419,422,424,426,428,430,432,433,436,438,440,442,445,447,449,450,454,456,458,460,462,465,467,470,472,474,476,480,482,484],[164,44,48,241,165,44],"project\u002Fneutral\u002Fidea",[226,44,44,241,11,33],[244,44,44,245,246,44],"36888614","other\u002Fneutral\u002Fnone","lalwanivikas",[229,44,44,248,11,33],"project\u002Fpositive\u002Fdesign",[250,44,48,251,165,44],"36899804","project\u002Fneutral\u002Fdesign",[253,44,44,245,254,44],"36889138","Aperocky",[256,44,44,245,257,44],"36892441","thumbuddy",[259,44,44,245,260,44],"36896192","johnfn",[262,44,44,245,254,44],"36896980",[264,44,44,245,165,44],"36899780",[266,44,44,267,254,44],"36900239","commenter\u002Fcritical\u002Fnone",[269,44,44,270,165,44],"36900540","commenter\u002Fneutral\u002Fnone",[272,44,44,267,254,44],"36901504",[274,44,44,245,275,44],"36889292","bvm",[277,33,48,241,278,44],"36887435","eikenberry",[232,33,44,280,11,33],"project\u002Fneutral\u002Fexecution",[282,33,48,280,176,44],"36888832",[284,33,48,280,139,44],"36889009",[286,33,44,251,11,33],"36889650",[288,38,33,289,290,44],"36886863","project\u002Fcritical\u002Fprivacy","cassianoleal",[85,38,44,292,11,33],"project\u002Fneutral\u002Fprivacy",[294,38,33,289,295,44],"36887777","Galanwe",[297,38,44,292,11,33],"36888086",[299,38,33,289,295,44],"36888337",[301,38,44,302,11,33],"36888376","maker\u002Fneutral\u002Fprivacy",[304,38,18,305,295,44],"36890126","maker\u002Fpositive\u002Fnone",[307,38,33,308,290,44],"36933468","project\u002Fcritical\u002Fexecution",[183,48,48,310,184,44],"project\u002Fneutral\u002Fperformance",[312,48,44,310,11,33],"36887082",[314,48,48,315,316,44],"36903105","project\u002Fneutral\u002Fdocs","petespeed",[318,48,44,315,11,33],"36909038",[219,320,33,321,116,44],4,"project\u002Fcritical\u002Fdesign",[205,320,44,323,206,44],"other\u002Fneutral\u002Fidea",[325,320,18,326,116,44],"36887722","project\u002Fpositive\u002Fnone",[328,320,44,245,329,44],"36890696","lgrammel",[331,320,44,245,332,44],"36891918","bsenftner",[334,320,44,241,11,33],"36887238",[336,320,33,337,338,44],"36890022","project\u002Fcritical\u002Fidea","ldhough",[340,320,44,341,342,44],"36891533","commenter\u002Fneutral\u002Fidea","Philpax",[344,320,44,345,11,33],"36894826","maker\u002Fneutral\u002Fidea",[115,320,18,248,116,44],[348,320,44,305,11,33],"36915773",[350,320,44,245,351,44],"36887717","estebarb",[353,320,44,245,116,44],"36888481",[355,320,44,245,356,44],"36890625","sqs",[358,320,44,359,116,44],"36898559","other\u002Fneutral\u002Fdesign",[361,320,44,245,362,44],"36910134","damc4",[212,18,44,245,213,44],[365,18,44,241,11,33],"36887154",[111,42,48,241,112,44],[368,42,44,369,11,33],"36886098","project\u002Fpositive\u002Fidea",[371,42,33,337,372,44],"36889359","specproc",[374,42,44,245,112,44],"36889386",[376,42,44,245,372,44],"36892231",[378,236,48,315,379,44],"36885645","weekay",[381,236,44,382,11,33],"36885898","project\u002Fneutral\u002Fnone",[104,384,18,385,105,44],8,"project\u002Fpositive\u002Fexecution",[387,384,48,310,388,44],"36885736","mritchie712",[390,384,48,310,105,44],"36885873",[134,392,48,393,135,44],9,"project\u002Fneutral\u002Fpricing",[65,392,44,395,11,33],"maker\u002Fneutral\u002Fpricing",[397,392,44,245,176,44],"36888891",[399,392,44,400,11,33],"36889186","maker\u002Fneutral\u002Fnone",[123,402,33,289,124,44],10,[404,402,44,302,11,33],"36886197",[406,402,18,407,124,44],"36886284","maker\u002Fpositive\u002Fprivacy",[409,31,48,382,139,44],"36889141",[411,31,44,305,11,33],"36889236",[138,34,48,292,139,44],[414,34,44,292,11,33],"36889139",[416,417,44,245,418,44],"36906710",13,"ppipada",[175,420,48,421,176,44],14,"project\u002Fmixed\u002Fidea",[423,420,44,345,11,33],"36888079",[425,420,18,369,176,44],"36888781",[427,420,18,369,176,44],"36888938",[429,420,44,369,11,33],"36889180",[153,431,48,382,154,44],15,[198,431,44,400,11,33],[434,431,18,326,435,44],"36886544","vunderba",[127,437,33,289,128,44],16,[439,437,44,302,11,33],"36889429",[441,437,18,407,128,44],"36889489",[443,437,33,289,444,44],"36889519","deanc",[446,437,44,302,11,33],"36889626",[145,223,33,448,146,44],"project\u002Fcritical\u002Fpricing",[68,223,44,395,11,33],[451,223,44,452,453,44],"36902089","commenter\u002Fneutral\u002Fpricing","faeranne",[100,455,18,248,101,44],18,[457,455,44,400,11,33],"36886022",[157,459,48,400,158,44],19,[461,459,44,400,11,33],"36894861",[463,459,18,326,464,44],"36901058","jshreder",[466,32,33,308,260,44],"36885861",[468,32,44,469,11,33],"36885943","maker\u002Fneutral\u002Fexecution",[171,471,48,241,172,44],21,[473,471,44,245,213,44],"36891091",[475,471,44,469,11,33],"36895068",[477,478,48,241,479,44],"36886629",22,"mr_o47",[481,478,44,345,11,33],"36886715",[190,483,48,393,191,44],23,[485,483,48,393,486,44],"36892210","HanClinto",[],[489,494,499,503,507,511],{"id":490,"name":491,"points":492,"category":493},"36860953","pycareer.io",945,"web_saas",{"id":495,"name":496,"points":497,"category":498},"36849502","ProjectionLab",766,"finance_crypto",{"id":500,"name":501,"points":502,"category":493},"36860898","Invoice Dragon",564,{"id":504,"name":505,"points":506,"category":493},"36813086","Primo",356,{"id":508,"name":509,"points":510,"category":493},"36836596","cc.dev",302,{"id":512,"name":513,"points":514,"category":515},"36802582","Ollama",284,"ai",false,"v2",{"id":519,"name":5,"line":6,"ai":516,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":520,"top":18,"kw":521,"maker":11,"domain":10,"tier":19,"attempts":44,"strip":522,"url":9,"mix":523,"praise":97,"objection":120,"sub":21},36882146,-0.08,[24,25,26,27],"3300033111331501500313530153353331533333",[31,32,33,34],1793991070159]