[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-researchers-propose-letting-world-models-forget-selectively":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},10068,"researchers-propose-letting-world-models-forget-selectively","Researchers Propose Letting World Models Forget Selectively","A new paper argues AI world models need two memory speeds: permanent physics and fast-changing facts, exposing a blind spot in forgetting benchmarks.","A new paper argues AI world models should be allowed to forget - just not everything.\n\nResearchers posted the paper on arXiv on October 5, 2026, arguing that continual learning's usual rule - any drop in performance on old data counts as failure - breaks down for world models. World models predict an environment that changes over time, so a fact that was true when learned can become false later, and updating it is correct behavior, not a bug. The authors propose splitting a model's knowledge into two tiers: invariants like physics and object permanence that must never be revised, and instance-level facts that should be revised the moment the environment changes. They introduce a new evaluation approach, differential retention, which tracks regression on the invariants separately from how quickly the model updates its instance-level facts, rather than blending both into a single forgetting score.\n\nThat distinction matters because current benchmarks can't tell a model that wisely updated outdated knowledge apart from one that's quietly falling apart - both look like \"forgetting,\" so today's tests just reward whichever model changes the least. That's a real liability for anyone building robots or long-running agents meant to operate in persistent, shifting environments, rather than one-shot chatbots that never have to track a world that moves on without them.\n\nIt's a useful reminder that \"catastrophic forgetting\" isn't always catastrophic - sometimes forgetting is the only way a model stays right.","[\"ai\",\"world-models\",\"continual-learning\",\"machine-learning\"]","2026-10-05T04:00:00.000Z","2026-10-05T21:26:41.554Z","2026-10-05T21:26:47.566Z","published",null,[],"ai",[24,26,27,28],"world-models","continual-learning","machine-learning",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.03713",0,{"sections":35},[36,39,43,48,53,58,62,67,71,76,81,86,91,96],{"name":37,"slug":24,"count":38,"latest_published_at":18},"AI",6290,{"name":40,"slug":41,"count":42,"latest_published_at":18},"Security","security",869,{"name":44,"slug":45,"count":46,"latest_published_at":47},"Policy","policy",444,"2026-10-03T15:02:01.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",323,"2026-10-04T13:00:00.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",204,"2026-10-03T14:50:50.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":18},"Science","science",178,{"name":63,"slug":64,"count":65,"latest_published_at":66},"Consumer Tech","consumer-tech",158,"2026-10-03T03:21:12.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":18},"Dev Tools","dev-tools",98,{"name":72,"slug":73,"count":74,"latest_published_at":75},"Software","software",97,"2026-10-04T10:00:00.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Startups","startups",92,"2026-10-04T14:36:25.000Z",{"name":82,"slug":83,"count":84,"latest_published_at":85},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":87,"slug":88,"count":89,"latest_published_at":90},"General","general",51,"2026-10-05T02:35:01.000Z",{"name":92,"slug":93,"count":94,"latest_published_at":95},"Reviews","reviews",32,"2026-10-02T18:00:00.000Z",{"name":97,"slug":98,"count":99,"latest_published_at":100},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]