[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-new-study-catches-chatbots-ignoring-revoked-instructions":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":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},4939,"new-study-catches-chatbots-ignoring-revoked-instructions","New Study Catches Chatbots Ignoring Revoked Instructions","A new benchmark shows LLMs often keep obeying constraints users revoked mid-chat, and finds a fix that reliably reduces the problem.","Tell a chatbot to drop a rule mid-conversation, and there's a decent chance it keeps following it anyway.\n\nResearchers built a system that catches large language models still enforcing constraints a user has explicitly revoked, a bug they call 'behavioral relapse.' The tool logs every constraint and its status in a running ledger, marks withdrawn rules as dead ('tombstoned'), and compiles what's actually still in force into one clean instruction set before the model responds. A second component probes each turn to predict relapse before the reply goes out, and a third tries repair strategies under a fixed compute budget. Tested on coding tasks built from HumanEval, an 8-billion-parameter model relapsed more often as the pile of constraints grew, while larger models mostly avoided the problem. Precompiling the live constraint set before generation cut relapse significantly compared with a baseline that just re-checks the output after the fact; layering more elaborate repair steps on top added no measurable benefit, and simply appending a one-line note that a rule is dead recovered roughly a third of the fix's effect.\n\nThis matters because relapse is a quiet failure mode. A model that adds a wrong fact is easy to spot; a model that keeps a feature you asked it to remove, or reinstates a rule you told it to drop, looks like it's working right up until you check the output closely. That's a live risk for coding assistants and agents running long sessions, where instructions pile up and get revised constantly. It also reframes instruction-following as something that has to hold across edits, not just at first read.\n\nThe fix works, but it takes real engineering: a constraint ledger, a prediction probe, and extra API calls layered onto every turn. Most chatbot products aren't running anything like that today, so until they do, 'never mind' is more of a suggestion than a command.","[\"ai research\",\"llms\",\"multi-turn dialogue\",\"arxiv\"]","2026-08-14T04:00:00.000Z","2026-08-14T19:25:44.061Z","2026-08-14T19:25:55.864Z","published",null,[],"ai",[26,27,28,29],"ai research","llms","multi-turn dialogue","arxiv",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.12599",0,{"sections":36},[37,41,45,50,55,60,65,70,75,80,85,90,95,100],{"name":38,"slug":24,"count":39,"latest_published_at":40},"AI",3293,"2026-08-20T04:00:00.000Z",{"name":42,"slug":43,"count":44,"latest_published_at":40},"Security","security",435,{"name":46,"slug":47,"count":48,"latest_published_at":49},"Policy","policy",210,"2026-08-19T09:32:27.000Z",{"name":51,"slug":52,"count":53,"latest_published_at":54},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":56,"slug":57,"count":58,"latest_published_at":59},"Hardware","hardware",140,"2026-08-19T18:25:42.000Z",{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Science","science",90,"2026-08-19T18:41:02.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Dev Tools","dev-tools",69,"2026-08-18T04:00:00.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Startups","startups",47,"2026-08-19T19:13:46.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"General","general",33,"2026-08-18T22:18:13.000Z",{"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"]