{"schemaVersion":1,"editionId":"2026-09-14","title":"AI video editing research, and a DeepSeek routing check","dek":"A study separates previews, summaries and trailers; current DeepSeek documentation distinguishes continued V4 Pro service from rerouted legacy Flash names.","coverageNote":"Partial September 14 scan, Europe/Berlin. With no completed prior cutoff, the assumed window is September 13, 12:38:25 to September 14, 12:38:25 CEST. Includes catch-up coverage of a September 11 preprint and a current-documentation guide; neither is presented as a new launch today. Sources were read after cutoff. Prior editions were checked. Original X access failed and older gaps remain unreviewed; no completed research cutoff is advanced.","summaryIntro":"A useful editing experiment asks different questions of previews and trailers. For developers, a separate documentation check explains which DeepSeek model names still point to their original model.","publishedAt":"2026-09-14T10:46:05.430Z","updatedAt":"2026-09-14T10:46:05.430Z","version":1,"items":[{"id":"agentic-video-editing-study","kind":"quick-update","thumbnail":{"src":"/api/media/thumbnails/2026-09-14/agentic-video-editing-study/d0ab6a802ebdd5d59328aa446c927a03ba83b762d5bc0489208392dc3587bdce","alt":"Editorial collage of film strips and three landscape cards, headed One Episode, Three Cuts: Research Preprint.","credit":"AI Daywire · AI-assisted editorial illustration","kind":"editorial-illustration"},"title":"Catch-up: video-editing study gives previews, summaries and trailers different goals","category":"Creativity & Media","tags":["video","research"],"eventDate":"2026-09-11","status":["research-preprint"],"sourceIds":["V1","V2"],"short":"A September 11 preprint tests three editing workflows on five TV episodes. Its evaluations rely on AI judges and model quizzes, so they do not establish audience response.","claims":[{"text":"The study uses five episodes from one scripted television production.","sourceIds":["V2"]},{"text":"The preprint was submitted September 11.","sourceIds":["V1"]}],"long":[{"text":"Nath and colleagues describe agents working from timestamped episode, scene and shot descriptions. Previews aim to attract attention without spoilers; summaries prioritize information; trailers allow more creative rearrangement. The experiments cover five episodes of one show.","sourceIds":["V2"]},{"text":"The paper uses LLM preference judgments and a model-answering quiz. The authors call for broader testing and flag costs and cascading errors in long agent workflows. This is a preprint, not independently reproduced evidence of viewer engagement or a released editing product.","sourceIds":["V2"]}]},{"id":"deepseek-model-routing-guide","kind":"guide","thumbnail":{"src":"/api/media/thumbnails/2026-09-14/deepseek-model-routing-guide/8fcc2d983c4974e87027cb1ac826996b60dfe3c5caddceb1e7e95e0f5cdde42a","alt":"Editorial paper collage of code cards linked by straight and merging arrows, headed Check Model Routing: DeepSeek Guide.","credit":"AI Daywire · AI-assisted editorial illustration","kind":"editorial-illustration"},"title":"Guide: distinguish DeepSeek V4 Pro continuation from Flash alias routing","category":"Models & Agents","tags":["models","coding","guides"],"eventDate":"2026-09-14","status":["reported"],"sourceIds":["D1","D2"],"short":"DeepSeek's current docs say V4 Pro service will continue after September 14 with unchanged billing. Older Flash aliases route to V4.1 Flash. Documentation-based; not hands-on tested.","claims":[{"text":"The current documentation says V4 Pro API service will continue after September 14 with its billing method unchanged.","sourceIds":["D1","D2"]},{"text":"The two legacy Flash names are documented as serving V4.1 Flash.","sourceIds":["D2"]}],"long":[{"text":"Check the model name in your integration against the live table. DeepSeek lists deepseek-v4-pro as V4-Pro-0813 and says service will continue after September 14 with unchanged billing, subject to further notice. The continuation statement has no separate amendment date; this guide checks current documentation rather than dating that decision.","sourceIds":["D1","D2"]},{"text":"For Flash, the docs recommend deepseek-flash. The accepted legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily serve V4.1 Flash at Flash prices. The table marks vision support for Flash, but not Pro. These distinctions are worth checking before changing a production configuration. Documentation-based; not hands-on tested.","sourceIds":["D1","D2"]}]}],"sources":[{"id":"V1","title":"Unified Agentic Video Editing Across Levels of Complexity and Creativity","publisher":"Nath et al. / arXiv","url":"https://arxiv.org/abs/2609.12769","publishedDate":"2026-09-11","kind":"research-preprint"},{"id":"V2","title":"Unified Agentic Video Editing Across Levels of Complexity and Creativity — full text","publisher":"Nath et al. / arXiv","url":"https://arxiv.org/html/2609.12769v1","publishedDate":"2026-09-11","kind":"research-preprint"},{"id":"D1","title":"Change Log — September 10 entry, current text","publisher":"DeepSeek","url":"https://api-docs.deepseek.com/updates/","publishedDate":"2026-09-10","kind":"official-documentation"},{"id":"D2","title":"Models & Pricing","publisher":"DeepSeek","url":"https://api-docs.deepseek.com/quick_start/pricing/","publishedDate":null,"kind":"official-documentation"}],"review":{"passed":true,"reviewedAt":"2026-09-14T10:45:34.519Z","method":"source-check"},"corrections":[],"canonicalUrl":"https://aidaywire.com/briefings/2026-09-14","language":"en","aiGenerated":true,"summary":"A useful editing experiment asks different questions of previews and trailers. For developers, a separate documentation check explains which DeepSeek model names still point to their original model.\n\nA September 11 preprint tests three editing workflows on five TV episodes. Its evaluations rely on AI judges and model quizzes, so they do not establish audience response.\n\nDeepSeek's current docs say V4 Pro service will continue after September 14 with unchanged billing. Older Flash aliases route to V4.1 Flash. Documentation-based; not hands-on tested.","fullText":"Catch-up: video-editing study gives previews, summaries and trailers different goals\n\nNath and colleagues describe agents working from timestamped episode, scene and shot descriptions. Previews aim to attract attention without spoilers; summaries prioritize information; trailers allow more creative rearrangement. The experiments cover five episodes of one show.\n\nThe paper uses LLM preference judgments and a model-answering quiz. The authors call for broader testing and flag costs and cascading errors in long agent workflows. This is a preprint, not independently reproduced evidence of viewer engagement or a released editing product.\n\nGuide: distinguish DeepSeek V4 Pro continuation from Flash alias routing\n\nCheck the model name in your integration against the live table. DeepSeek lists deepseek-v4-pro as V4-Pro-0813 and says service will continue after September 14 with unchanged billing, subject to further notice. The continuation statement has no separate amendment date; this guide checks current documentation rather than dating that decision.\n\nFor Flash, the docs recommend deepseek-flash. The accepted legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp temporarily serve V4.1 Flash at Flash prices. The table marks vision support for Flash, but not Pro. These distinctions are worth checking before changing a production configuration. Documentation-based; not hands-on tested.","checksum":"b02abdd5ebbb48d644cd92894cb2444df740e28a532591baf90bac8625878cab"}