[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-lego-speech-ai-holds-steady-on-multi-turn-math-tests":10,"sections":44},{"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":34,"tags":35,"sources":39,"feedback":43,"feedback_at":22,"cost_usd":43,"total_tokens":43},9205,"lego-speech-ai-holds-steady-on-multi-turn-math-tests","LEGO Speech AI Holds Steady on Multi-Turn Math Tests","A new benchmark shows LEGO held steady at 77.5 percent whether a problem arrived whole or in shards, while rivals lost 5 to 25 points.","Most voice AI assistants lose accuracy when a problem is revealed piece by piece across a conversation. One proprietary system did not budge.\n\nResearchers released SpeechConversationBench (SCB), a test built from 103 modified GSM8K math problems, to measure how speech-to-speech AI handles information that arrives across multiple turns instead of all at once. Each problem was delivered three ways: as a single spoken prompt, as the same details concatenated into one turn, and split into incremental turns resembling natural conversation. Across four commercial systems, including GPT-4o Realtime, accuracy on the incremental version fell 5.0 to 25.3 percentage points compared with the concatenated version. LEGO, a proprietary pipeline built by SCBX Innovation Lab with explicit conversational context tracking, scored 77.5 percent in all three conditions, while GPT-4o Realtime scored 76.6 percent on the incremental version.\n\nReal conversations rarely arrive in one clean block. People add details, backtrack, and clarify mid-thought, and an assistant that forgets the first half of a request once the second half shows up fails exactly where voice interfaces are supposed to shine. SCB turns that failure mode into a measurable number instead of an anecdote about a bad demo.\n\nA 103-problem math test from one lab is not proof LEGO has solved conversational memory, but it is a flat line next to four systems whose scores all bent downward.","[\"ai\",\"benchmarks\",\"voice-ai\",\"speech-recognition\"]","2026-10-01T04:00:00.000Z","2026-10-02T01:47:19.505Z","2026-10-02T01:47:23.116Z","published",null,[24,30],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"editor-r1","editor",1,"Define GSM8K on first use for general readers, and remove or attribute the unsupported claim that LEGO relies on 'off-the-shelf models' since the source never states what underlying models LEGO uses.","resolved",{"id":31,"reviewer":26,"round":32,"reason":33,"status":29},"editor-r2",2,"The dek says LEGO 'barely slips' but the body and source state LEGO held flat at 77.5 percent across all three conditions with no decline at all, so reword the dek to reflect that LEGO's score didn't move rather than implying a slight drop.","ai",[34,36,37,38],"benchmarks","voice-ai","speech-recognition",[40],{"name":41,"url":42},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.40198",0,{"sections":45},[46,49,53,57,62,67,71,76,81,85,90,95,100,105],{"name":47,"slug":34,"count":48,"latest_published_at":18},"AI",5612,{"name":50,"slug":51,"count":52,"latest_published_at":18},"Security","security",815,{"name":54,"slug":55,"count":56,"latest_published_at":18},"Policy","policy",430,{"name":58,"slug":59,"count":60,"latest_published_at":61},"Deals","deals",298,"2026-09-30T21:00:26.000Z",{"name":63,"slug":64,"count":65,"latest_published_at":66},"Hardware","hardware",196,"2026-09-30T13:00:00.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":18},"Science","science",163,{"name":72,"slug":73,"count":74,"latest_published_at":75},"Consumer Tech","consumer-tech",149,"2026-09-30T22:57:11.000Z",{"name":77,"slug":78,"count":79,"latest_published_at":80},"Dev Tools","dev-tools",93,"2026-10-01T02:30:48.000Z",{"name":82,"slug":83,"count":79,"latest_published_at":84},"Software","software","2026-09-30T21:41:11.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"Startups","startups",84,"2026-09-30T20:39:09.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Gaming","gaming",51,"2026-09-30T16:24:30.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":101,"slug":102,"count":103,"latest_published_at":104},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":106,"slug":107,"count":108,"latest_published_at":109},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]