[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-hidden-reasoning-in-llms-is-more-readable-than-you-think":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},3845,"hidden-reasoning-in-llms-is-more-readable-than-you-think","Hidden Reasoning in LLMs Is More Readable Than You Think","Researchers decoded what frontier models compute during silent filler tokens, recovering intermediate reasoning steps with 80-95% accuracy without any labels.","AI models can reason without showing their work — and a new paper suggests we can read that work anyway.\n\nResearchers tested two open-weights frontier models, DeepSeek V3 and Kimi K2, on tasks where the models produce correct answers using content-free filler tokens like dots or counting sequences instead of a visible chain-of-thought. Using attention maps, logit-lens readouts, and a technique called KV-cache transplants, the team traced exactly how the models routed reasoning through those silent positions. They then built an unsupervised decoding pipeline that takes only hidden states as input — no ground-truth labels, no fine-tuning — and recovered intermediate values with 80-95% accuracy across four task types: fact retrieval, numeric composition, string manipulation, and in-context computation.\n\nThe finding matters because filler-token reasoning has been treated as a blind spot for AI oversight: if a model produces an answer with no visible reasoning steps, behavioral monitoring has nothing to examine. This paper pushes back on that framing, arguing that monitorability is a property of the full computational trace, not just the tokens a model prints. That's a meaningful shift in how safety researchers might think about what's actually auditable inside a model.\n\nThe caveat is that this was demonstrated on specific, bounded tasks with two models — not a general proof that all hidden computation is recoverable. Whether the technique scales to longer reasoning chains or less structured problems is the next question nobody has answered yet.","[\"ai\",\"llm-safety\",\"interpretability\",\"research\"]","2026-07-07T04:00:00.000Z","2026-07-07T09:51:11.106Z","2026-07-07T09:51:13.985Z","published",null,[],"ai",[24,26,27,28],"llm-safety","interpretability","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2607.03502",0,{"sections":35},[36,40,45,50,55,60,65,70,75,79,84,88,93,98],{"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":18},"Dev Tools","dev-tools",59,{"name":80,"slug":81,"count":82,"latest_published_at":83},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":85,"slug":86,"count":82,"latest_published_at":87},"Startups","startups","2026-06-29T20:55:50.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"General","general",29,"2026-07-10T22:28:58.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]