[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-mapping-ai-personality-traits-in-model-weights":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},4550,"mapping-ai-personality-traits-in-model-weights","Mapping AI Personality Traits in Model Weights","Researchers used the OCEAN psychology framework to train adapters that dial individual personality traits up or down in large language models.","A research team has built a system for measuring, editing, and combining personality traits directly inside language model weights.\n\nThe paper, posted to arXiv, treats model behavior as positions in a \"personality space\" defined by the OCEAN framework — Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. The team trained low-rank adapters, small plug-in weight modifications, to amplify or suppress each trait independently across six models ranging from 4B to 32B parameters. They validated the results using an LLM-based judge calibrated against human raters, trait-specific benchmarks, and standard capability tests. The adapters also compose: stacking multiple trait adapters produces roughly additive effects, letting researchers dial up a \"conscientious but low-agreeableness\" model without retraining from scratch.\n\nThe safety implications are the part worth paying attention to. The researchers found that nudging a model along the neuroticism axis changed how it expressed frustration, while the agreeableness axis directly affected sycophancy — the well-documented tendency of models to tell users what they want to hear. That gives safety teams a concrete, measurable handle on behaviors that have mostly been managed through prompt engineering and RLHF guesswork.\n\nPersonality control in AI is not a new idea — character prompting has been a staple of chatbot products for years — but baking traits into weights rather than system prompts means the behavior is harder to talk the model out of, which is either a feature or a risk depending on who is deploying it.","[\"ai\",\"machine-learning\",\"safety\",\"llm\"]","2026-07-10T04:00:00.000Z","2026-07-10T04:34:59.718Z","2026-07-10T04:35:02.609Z","published",null,[],"ai",[24,26,27,28],"machine-learning","safety","llm",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.07916",0,{"sections":35},[36,40,45,50,55,60,65,70,75,80,85,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",2590,"2026-07-16T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":44},"Security","security",294,"2026-07-15T19:59:48.000Z",{"name":46,"slug":47,"count":48,"latest_published_at":49},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Policy","policy",158,"2026-07-16T00:02:48.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",122,"2026-07-14T19:46:26.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",93,"2026-07-13T13:20:48.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Software","software",70,"2026-07-13T19:52:25.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Science","science",66,"2026-07-10T10:29:37.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",59,"2026-07-07T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":86,"slug":87,"count":83,"latest_published_at":88},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",29,"2026-07-10T22:28:58.000Z",{"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"]