[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-this-edge-ai-engine-ditches-neural-nets-for-mandelbrot-math":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},7838,"this-edge-ai-engine-ditches-neural-nets-for-mandelbrot-math","This Edge AI Engine Ditches Neural Nets for Mandelbrot Math","Werr replaces neural network weights with Mandelbrot set math to make fast automated decisions, but its benchmark is tiny and the numbers need context.","A new system called werr claims it can handle simple automated decisions without a single neural network weight, using the geometry of the Mandelbrot set instead of a trained model.\n\nThe system, built on top of prior work called Mandelbrot Fractal Neural Synthesis and offered through the answerr.me platform, turns each request into a 24-byte coordinate seed and reads how that point escapes the Mandelbrot set to produce a yes\u002Fno answer, a category, or a score. It runs with zero stored weight tensors and reportedly zero bytes of VRAM. On JevBench, a 231-example benchmark, the authors report 81.65% calibrated accuracy and a 7.08ms median latency. A separate built-in filter for catching prompt injection attacks is faster still, reaching 3.31ms throughput latency after a 45.8% cut in processing steps, and the authors say it blocked 100% of injection attempts in testing - though their own 95% confidence interval on that number spans from 0% to 27.8%, meaning the real bypass rate is far from settled.\n\nThat distinction matters because a lot of what gets marketed as an AI decision - route this ticket, flag this transaction, rank these results - is really just a fast classification call, not a task that needs a large language model's reasoning. Companies already chase that gap with smaller distilled models and rule engines; werr's pitch is to skip stored weights altogether, and its authors even demonstrate it running as an on-chain oracle on EVM-compatible smart contracts for about 21,438 gas.\n\nA 231-example test set and a confidence interval wide enough to swallow its own headline claim suggest the fractal framing is doing more marketing work than the results can back up yet.","[\"ai\",\"edge-ai\",\"prompt-injection\",\"benchmarks\"]","2026-09-25T04:00:00.000Z","2026-09-26T01:37:00.600Z","2026-09-26T01:37:05.655Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Clarify that 3.31ms is the prompt-injection filter's accelerated throughput latency (not a JevBench figure) while 7.08ms is the actual JevBench median latency, since the draft currently conflates them as if both describe the 231-example benchmark, and add the source's wide 95% CI ([0.0%, 27.8%]) on the 0.0% bypass claim to back up the piece's own skepticism.","resolved","ai",[30,32,33,34],"edge-ai","prompt-injection","benchmarks",[36],{"name":37,"url":38},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.25498",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",4557,"2026-09-25T17:16:30.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Security","security",741,"2026-09-25T15:52:13.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",390,"2026-09-25T16:24:59.000Z",{"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",140,"2026-09-25T11:55:23.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Consumer Tech","consumer-tech",132,"2026-09-25T15:30:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Software","software",88,"2026-09-24T23:06:55.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Dev Tools","dev-tools",82,"2026-09-25T09:59:40.000Z",{"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"]