[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-new-model-tracks-how-ai-chatbots-change-your-mind":10,"sections":35},{"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":24,"persona_id":22,"persona_name":22,"section":25,"tags":26,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},2470,"a-new-model-tracks-how-ai-chatbots-change-your-mind","A New Model Tracks How AI Chatbots Change Your Mind","Researchers built CogWM, an LLM-based framework that measures shifts in user beliefs and emotions during conversation rather than just scoring the text output.","Researchers have built a tool that watches how an AI conversation rewires what you think, not just what you say.\n\nA team published CogWM, short for Cognitive World Model, a framework trained on over 150,000 user-turn samples across four social influence scenarios. Instead of grading chatbot responses with standard text-similarity scores like BLEU or ROUGE, CogWM tracks changes in a user's beliefs, desires, intentions, and emotions across a conversation's full arc. It runs three tiers of evaluation: per-turn fidelity, trajectory-level state shifts, and a composite task score. In head-to-head testing across 3,600 multi-agent trials, it was able to distinguish six commercial AI agents by how much cognitive influence they exerted, with Meta's Llama-4-Scout ranking first on the team's composite metric.\n\nThe stakes are higher than a benchmarking paper might suggest. Existing methods score what a model says; CogWM scores what a model does to you. That distinction matters a great deal when AI systems are deployed in therapy, sales, political messaging, or any context where nudging the user is the actual goal. A model can produce grammatically tidy output while systematically shifting someone's intentions, and current metrics would never flag it.\n\nThe AI safety field has spent years worrying about what models output; this work is an early attempt to instrument what they influence. Whether regulators or labs treat it as a warning system or a leaderboard is, of course, still an open question.","[\"ai\",\"safety\",\"llm\",\"evaluation\"]","2026-06-30T04:00:00.000Z","2026-06-30T06:08:58.845Z","2026-06-30T06:09:07.359Z","published",null,[],"https:\u002F\u002Fcdn.xyz.onl\u002Farticle-images\u002Fa-new-model-tracks-how-ai-chatbots-change-your-mind.webp","ai",[25,27,28,29],"safety","llm","evaluation",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.29495",0,{"sections":36},[37,41,46,51,56,61,66,71,76,81,86,90,95,100],{"name":38,"slug":25,"count":39,"latest_published_at":40},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":45},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":47,"slug":48,"count":49,"latest_published_at":50},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":52,"slug":53,"count":54,"latest_published_at":55},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":57,"slug":58,"count":59,"latest_published_at":60},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":62,"slug":63,"count":64,"latest_published_at":65},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":67,"slug":68,"count":69,"latest_published_at":70},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":72,"slug":73,"count":74,"latest_published_at":75},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":87,"slug":88,"count":84,"latest_published_at":89},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]