[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-bigger-ai-models-still-fail-at-personalizing-from-your-data":10,"sections":34},{"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":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},5077,"bigger-ai-models-still-fail-at-personalizing-from-your-data","Bigger AI Models Still Fail at Personalizing From Your Data","A new benchmark called LUNAR tested 19 LLMs on app-behavior logs and found that more data or bigger models don't guarantee better personalized answers.","A new benchmark just showed that feeding an AI your life doesn't automatically make it more helpful.\n\nResearchers built LUNAR, a benchmark that tests how well large language models personalize answers using long-running app-activity logs covering clothing, food, housing, and mobility - basically what you buy, eat, live in, and how you get around. Because real user logs are scarce and sensitive, the team generated synthetic versions through a multi-stage pipeline built to mimic real behavior patterns, then checked that the fakes tracked real-world distributions more closely than other synthetic benchmarks. They ran 19 mainstream LLMs against it and found that having access to someone's behavioral history is necessary but not sufficient. Neither a bigger model nor a longer context window reliably produced better personalized responses.\n\nThat's a useful gut check for an industry that keeps pitching \"more context, bigger model\" as the fix for every personalization problem. What actually helped was a model's ability to pick the right evidence across domains and stitch it together - pulling detailed, individual records outperformed compressed memory summaries. But that also means the most personalized answers came from models handling the most granular, most sensitive data, exactly the tradeoff privacy advocates have been warning about.\n\nIn other words: scale isn't the personalization silver bullet vendors keep implying, and the version of \"AI that really knows you\" that works best is also the version with the most to leak.","[\"ai\",\"llms\",\"personalization\",\"privacy\"]","2026-08-17T04:00:00.000Z","2026-08-17T09:14:47.434Z","2026-08-17T09:14:59.275Z","published",null,[],"ai",[24,26,27,28],"llms","personalization","privacy",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.05246",0,{"sections":35},[36,40,44,49,54,59,64,69,74,79,84,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",3293,"2026-08-20T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":39},"Security","security",435,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",210,"2026-08-19T09:32:27.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",140,"2026-08-19T18:25:42.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Science","science",90,"2026-08-19T18:41:02.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":78},"Dev Tools","dev-tools",69,"2026-08-18T04:00:00.000Z",{"name":80,"slug":81,"count":82,"latest_published_at":83},"Startups","startups",47,"2026-08-19T19:13:46.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":95,"slug":96,"count":97,"latest_published_at":98},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":100,"slug":101,"count":102,"latest_published_at":103},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]