[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-dataset-tracks-errors-in-a-21000-line-ai-only-codebase":10,"sections":40},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":30,"tags":31,"sources":35,"feedback":39,"feedback_at":22,"cost_usd":39,"total_tokens":39},7899,"new-dataset-tracks-errors-in-a-21000-line-ai-only-codebase","New Dataset Tracks Errors in a 21,000-Line AI-Only Codebase","A new arXiv study of a 21,000-line, all-Claude codebase found real errors in 14.3% of code-gen events and factual slips in about one in four chat replies.","An entire codebase written by AI, with every commit and error logged, just became a research subject.\n\nThe paper, \"Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase\" (arXiv:2609.29744, posted September 25, 2026), tracks the full development history of a 21,000-line Python tool built entirely by Claude, with no human-written code or tests anywhere in it. The authors built two code-provenance tracing tools and three taxonomies covering instruction intent, commit provenance, and response reliability, then applied all of it to the dataset. They found that instructions given to coding-agent CLIs skew toward comprehension, planning, and consultation rather than direct commands, and that development was mostly proactive rather than reactive. The headline numbers: 14.3% of code-generation events contained a real error later caught by the AI's own test suite, and roughly one in four to one in five of the AI's interactive responses contained a factual error.\n\nThis matters because most claims about AI coding reliability are anecdotal. Here is an actual error rate, measured against a real, working 21,000-line tool rather than a benchmark demo. It also quantifies a gap that matters for anyone letting an agent run unsupervised: the code errors get caught because the AI wrote its own tests, but the one-in-four factual error rate in conversational responses has no equivalent safety net.\n\nWorth noting: the AI graded its own homework. The test suite that caught those code errors was also AI-authored, so the 14.3% figure measures what the system was built to catch, not necessarily every bug that's actually in there.","[\"ai\",\"claude\",\"software-development\",\"research\"]","2026-09-25T04:00:00.000Z","2026-09-26T05:35:18.572Z","2026-09-26T05:35:23.502Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Add proper sourcing — the draft never names the actual source (arXiv paper title, arXiv ID\u002Flink, or publication date), which is required for a research-data story; cite the paper (e.g. 'Between the Commits...', arXiv:2609.29744, posted September 2026) instead of the vague 'researchers released a dataset.'","resolved","ai",[30,32,33,34],"claude","software-development","research",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.29744",0,{"sections":41},[42,46,51,56,61,66,71,76,81,86,91,96,101,106],{"name":43,"slug":30,"count":44,"latest_published_at":45},"AI",4624,"2026-09-25T21:57:05.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Security","security",748,"2026-09-26T01:30:00.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",392,"2026-09-25T18:44:30.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Deals","deals",256,"2026-09-25T17:00:53.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Hardware","hardware",185,"2026-09-25T15:00:22.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Science","science",143,"2026-09-25T22:28:02.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Consumer Tech","consumer-tech",133,"2026-09-26T07:30:06.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Software","software",90,"2026-09-25T20:55:00.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Dev Tools","dev-tools",84,"2026-09-26T04:20:58.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"Startups","startups",76,"2026-09-25T18:33:59.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"General","general",46,"2026-09-25T02:12:57.000Z",{"name":102,"slug":103,"count":104,"latest_published_at":105},"Reviews","reviews",30,"2026-09-24T20:07:31.000Z",{"name":107,"slug":108,"count":109,"latest_published_at":110},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]