[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-compression-trick-stops-ai-models-from-repeating-themselves":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},5706,"a-compression-trick-stops-ai-models-from-repeating-themselves","A Compression Trick Stops AI Models From Repeating Themselves","Researchers used a classic compression algorithm to stop AI models from repeating themselves, even at temperature zero.","A new decoding method called the LZ penalty fixes a long-standing annoyance in AI text generation: models that get stuck looping the same phrase.\n\nResearchers built the penalty on the codelengths from LZ77, the decades-old lossless compression algorithm behind formats like zip and gzip. The idea borrows from a well-known duality between compression and prediction: text that compresses well is text a model finds highly predictable, so penalizing the compressible parts pushes sampling toward the residual, less repetitive distribution. In tests, the method let state-of-the-art open-source reasoning models run at temperature zero, meaning greedy decoding, with no drop in capability and no degenerate repetition. The industry-standard frequency and repetition penalties, by contrast, still produced repetition rates as high as 4% in the same tests.\n\nThat 4% failure rate matters because temperature zero is the setting developers reach for when they want reproducible, deterministic output - exactly the case where a model looping is most likely to end up in a support ticket. A repetition fix that costs nothing in capability is rarer than it sounds; most guardrails trade some quality for safety.\n\nCompression and language modeling have been theoretically linked for years, but this is a practical reminder that the connection still has unmined value even as everyone's attention has moved on to bigger training runs.","[\"ai\",\"llms\",\"text-generation\",\"research\"]","2026-08-19T04:00:00.000Z","2026-08-19T13:18:59.197Z","2026-08-19T13:19:11.088Z","published",null,[],"ai",[24,26,27,28],"llms","text-generation","research",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2504.20131",0,{"sections":35},[36,40,44,49,54,59,64,69,74,79,84,89,94,99],{"name":37,"slug":24,"count":38,"latest_published_at":39},"AI",3293,"2026-08-20T04:00:00.000Z",{"name":41,"slug":42,"count":43,"latest_published_at":39},"Security","security",435,{"name":45,"slug":46,"count":47,"latest_published_at":48},"Policy","policy",210,"2026-08-19T09:32:27.000Z",{"name":50,"slug":51,"count":52,"latest_published_at":53},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":55,"slug":56,"count":57,"latest_published_at":58},"Hardware","hardware",140,"2026-08-19T18:25:42.000Z",{"name":60,"slug":61,"count":62,"latest_published_at":63},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":65,"slug":66,"count":67,"latest_published_at":68},"Science","science",90,"2026-08-19T18:41:02.000Z",{"name":70,"slug":71,"count":72,"latest_published_at":73},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":75,"slug":76,"count":77,"latest_published_at":78},"Dev Tools","dev-tools",69,"2026-08-18T04:00:00.000Z",{"name":80,"slug":81,"count":82,"latest_published_at":83},"Startups","startups",47,"2026-08-19T19:13:46.000Z",{"name":85,"slug":86,"count":87,"latest_published_at":88},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":90,"slug":91,"count":92,"latest_published_at":93},"General","general",33,"2026-08-18T22:18:13.000Z",{"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"]