[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-framework-teaches-ai-to-mimic-real-peoples-reactions":10,"sections":41},{"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":30,"persona_id":22,"persona_name":22,"section":31,"tags":32,"sources":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},7089,"new-framework-teaches-ai-to-mimic-real-peoples-reactions","New Framework Teaches AI to Mimic Real People's Reactions","A new framework models situational behavior, not just wording, to make AI role-play of real social media users more convincing.","A new AI framework tries to make chatbots react like the specific person they're imitating, not just echo how that person talks.\n\nResearchers built a method called Situation-Internal state-Behavior persona, which generates replies by modeling how a person's internal state and the situation they're in shape their behavior, rather than leaning on in-context learning that just feeds a model examples of past posts. Tested on a newly built dataset of social media replies, the method beat existing in-context learning baselines. Because it's hard for an LLM judge to grade an impersonation of someone it doesn't already know well, the team also built an evaluation protocol that hands the AI judge reference material about the person being impersonated; that protocol, not the impersonation method itself, is what achieved moderate correlation with human judgment. The method also held up on fictional-character benchmarks, suggesting the behavioral approach isn't limited to real people's social posts.\n\nThe real problem here is familiar to anyone who has used an AI persona bot: it can recite someone's opinions but still feels off because it doesn't react the way that person would under pressure or in context. Fixing the evaluation side may matter more than the modeling trick, since it's been genuinely hard to score these systems when the judge can't independently verify facts about an obscure person.\n\nModerate correlation with human judgment is a modest result, and a benchmark built by the same team that built the method is worth watching rather than taking at face value.","[\"ai\",\"llm\",\"role-playing\",\"social-media\"]","2026-09-21T04:00:00.000Z","2026-09-21T05:49:10.889Z","2026-09-21T05:49:22.727Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Cut or attribute the unsourced claims that voice-cloning AI is 'quietly becoming a real product category' and that 'most of those tools fail the same way' with a 'flat affect' — none of that is in the source paper and reads as invented market context; also fix the muddled claim that 'the method... showed moderate correlation with human judgment,' since the source attributes that correlation to the evaluation protocol, not the impersonation method's performance.","resolved","https:\u002F\u002Fcdn.xyz.onl\u002Farticle-images\u002Fnew-framework-teaches-ai-to-mimic-real-peoples-reactions.webp","ai",[31,33,34,35],"llm","role-playing","social-media",[37],{"name":38,"url":39},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.21349",0,{"sections":42},[43,46,50,55,60,65,70,75,80,85,90,95,100,105],{"name":44,"slug":31,"count":45,"latest_published_at":18},"AI",4158,{"name":47,"slug":48,"count":49,"latest_published_at":18},"Security","security",679,{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",350,"2026-09-20T20:32:43.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Hardware","hardware",156,"2026-09-19T11:00:00.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Science","science",130,"2026-09-20T13:48:11.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Consumer Tech","consumer-tech",99,"2026-09-09T17:27:33.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",78,"2026-09-18T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Software","software",75,"2026-09-10T20:41:21.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Startups","startups",55,"2026-09-09T23:14:29.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Gaming","gaming",43,"2026-09-10T12:18:06.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"General","general",42,"2026-09-18T22:35:10.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":106,"slug":107,"count":108,"latest_published_at":109},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]