{"id":"jiahui-yu","title":"Jiahui Yu","content":"**Jiahui Yu** is an artificial intelligence researcher and entrepreneur known for his work on multimodal models, computer vision, generative AI, and reasoning models. He previously co-founded TBD Lab within [Meta Superintelligence Labs](https://iq.wiki/wiki/meta-superintelligence-team), led perception research at OpenAI, and co-led the multimodal component of Google's Gemini project at Google DeepMind. In August 2026, Yu announced his departure from Meta to start a new company. [\\[7\\]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b)  [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35) \n\n# Education\n\nYu earned a Bachelor of Science degree in Computer Science from the University of Science and Technology of China. He later completed a PhD at the University of Illinois Urbana-Champaign, where his research focused on deep learning, computer vision, and efficient neural networks. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) \n\n# Career\n\nYu began his research career as an intern at Microsoft Research Asia from May to December 2015, where he worked on large-scale deep learning training systems. In early 2016, he joined Megvii Research as a research intern, focusing on object detection and contributing to UnitBox. Between June 2016 and May 2018, he also worked as a research consultant at Jump Trading, developing models involving financial data. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[6\\]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf) \n\nFrom May to December 2017, Yu interned at Adobe Research, where his work included generative adversarial networks and image inpainting. Projects associated with this period included DeepFill and subsequent work on image completion. From January to August 2018, he worked at Snap Research on efficient deep learning models, including Slimmable Networks. He later interned at Baidu Research, Nvidia Research, and Google Brain, working on areas including AutoML, efficient neural networks, and generative models. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[6\\]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf) \n\n### Google and Google DeepMind\n\nYu joined Google as a research scientist in February 2020. His work included automatic speech recognition, multimodal representation learning, computer vision, and generative models. He later became a senior research scientist and subsequently worked at Google DeepMind. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[6\\]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf) \n\nAt Google DeepMind, Yu co-led the multimodal pillar of Gemini, Google's multimodal AI model family. He also worked on multimodal understanding and generation and contributed to research associated with Google's transition toward large-scale multimodal foundation models.\n\nYu left Google DeepMind in 2023. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) \n\n### OpenAI\n\nIn October 2023, Yu joined OpenAI, where he led the Perception team. His work focused on multimodal capabilities that allow AI models to process and reason over information such as images alongside text. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[6\\]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf) \n\nAccording to Yu's personal website, he contributed to several OpenAI model releases. He worked on data, encoders, pre-training, and post-training for GPT-4o and later served as a pre-training data individual contributor and post-training adviser for GPT-4o's image-generation capabilities. Yu was the project lead for OpenAI's Thinking with Images work, the multimodal post-training lead for o3, and the directly responsible individual for o4-mini from pre-training through post-training. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) \n\nYu left OpenAI in 2025 to join Meta's newly formed superintelligence organization. [\\[2\\]](#cite-id-df9f59f1-2422-4e3e-9951-cd21dc1947df)  [\\[3\\]](#cite-id-fb95d7db-dcbb-4821-97a4-b691303930f0) \n\n### Meta Superintelligence Labs and TBD Lab\n\nYu joined Meta's superintelligence initiative in 2025 as the company was recruiting researchers from organizations including OpenAI, Google DeepMind, and Anthropic. Meta formally organized [Meta Superintelligence Labs ](https://iq.wiki/wiki/meta-superintelligence-team)(MSL) in June 2025 as part of a broader effort to develop advanced foundation models and pursue superintelligence. [\\[2\\]](#cite-id-df9f59f1-2422-4e3e-9951-cd21dc1947df)  [\\[3\\]](#cite-id-fb95d7db-dcbb-4821-97a4-b691303930f0) \n\nAt Meta, Yu co-founded TBD Lab, a model-development team within Meta Superintelligence Labs, and led its multimodal work. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)  [\\[9\\]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17) \n\nDuring his tenure, Yu's multimodal team worked on Muse Spark, Voice Mode, Muse Image, and Muse Video. Yu identifies himself as multimodal pod lead for Muse Spark 1.0, 1.1, and 1.2, as well as Muse Image and Muse Video. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) \n\nMuse Spark was introduced in 2026 as part of Meta's next generation of AI models. Subsequent releases and projects from the team expanded into voice, image generation, video generation, coding, agentic tasks, and multimodal capabilities. [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)  [\\[9\\]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17) \n\nYu described building TBD Lab alongside Meta CEO Mark Zuckerberg and Meta Chief AI Officer Alexandr Wang as an important part of his time at the company. He left Meta in August 2026, approximately fourteen months after joining. [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)  [\\[9\\]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17)  [\\[7\\]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b) \n\n### New Company\n\nIn August 2026, Yu announced that he was leaving Meta to start a new company. [\\[7\\]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b)  [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)  [\\[9\\]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17)  [\\[10\\]](#cite-id-0c86fd0e-1b8e-4fea-8b25-740579aff3bf)  [\\[11\\]](#cite-id-e7ea5506-41c7-4717-97e8-42453956aec0) \n\nIn announcing the move, Yu said that over time he had become increasingly interested in a problem that he believes could have significant implications for humanity's future but remains comparatively underexplored. He said that the problem had become his primary focus and that he would disclose more information as the work developed. [\\[7\\]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b)  [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)  [\\[9\\]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17) \n\nAs of August 2026, Yu has not publicly disclosed the name of the new company, its specific research or product focus, its other founders or team members, or its funding arrangements. His personal website currently describes his status simply as \"starting a new company.\" [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)  [\\[9\\]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17) \n\nThe new company is separate from TBD Lab, which Yu co-founded while working at Meta. TBD Lab remains part of Yu's previous work at Meta rather than the name of the venture he announced after his departure. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)  [\\[8\\]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35) \n\n### Selected Work\n\nYu lists a number of major multimodal and foundation-model projects among his selected work:\n\n* Muse Spark 1.0, 1.1 and 1.2 — multimodal pod lead at Meta\n* Muse Image and Muse Video — multimodal pod lead at Meta\n* Thinking with Images — project lead at OpenAI\n* o3 — multimodal post-training lead at OpenAI\n* o4-mini — directly responsible individual from pre-training through post-training at OpenAI\n* GPT-4o image generation — pre-training data contributor and post-training adviser at OpenAI\n* GPT-4o — contributor across data, encoder development, pre-training, and post-training\n* Gemini — co-lead of the multimodal pillar at Google DeepMind\n\nYu's earlier research also includes work in computer vision, neural-network efficiency, image generation, image inpainting, multimodal representation learning, and automatic speech recognition. [\\[1\\]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) \n\n# Interviews\n\nYu has discussed his research in public interviews and technical presentations. In an episode of Google's Meet a Google Researcher, Yu and researcher Yonghui Wu discussed Parti, an autoregressive text-to-image model. The discussion covered Parti's approach to representing image generation as a sequence-modeling problem, scaling text-to-image models, multimodal research, and the development of increasingly capable generative systems. [\\[4\\]](#cite-id-75747682-590a-40bb-bb90-a56a9941c73e) \n\n[YOUTUBE@VID](https://youtube.com/watch?v=hvSetkAl654)","summary":"Jiahui Yu is an AI researcher known for his work on deep learning and high-performance computing. He is a member of Meta's Superintelligence Labs and previously...","images":[{"id":"QmU7nbWe2EbKLMRXYoJVu8PhxggAoUjkimT31ddPQj415W","type":"image/jpeg, image/png"}],"categories":[{"id":"people","title":"People in crypto"}],"tags":[{"id":"Developer"}],"media":[{"id":"https://www.youtube.com/watch?v=hvSetkAl654","size":null,"name":"hvSetkAl654","type":null,"source":"YOUTUBE"}],"metadata":[{"id":"references","value":"[{\"id\":\"ade53904-907e-4867-b1fb-4c1cf9fc234c\",\"url\":\"https://jiahuiyu.com/\",\"description\":\"Jiahui Yu — Personal Website\",\"timestamp\":1786930027280},{\"id\":\"df9f59f1-2422-4e3e-9951-cd21dc1947df\",\"url\":\"https://www.cnbc.com/2025/06/30/mark-zuckerberg-creating-meta-superintelligence-labs-read-the-memo.html\",\"description\":\"CNBC — Mark Zuckerberg creating Meta Superintelligence Labs: read the memo\",\"timestamp\":1786930027280},{\"id\":\"fb95d7db-dcbb-4821-97a4-b691303930f0\",\"url\":\"https://www.reuters.com/business/meta-deepens-ai-push-with-superintelligence-lab-source-says-2025-06-30/\",\"description\":\"Reuters — Meta deepens AI push with 'Superintelligence' lab\",\"timestamp\":1786930027280},{\"id\":\"75747682-590a-40bb-bb90-a56a9941c73e\",\"url\":\"https://www.youtube.com/watch?v=hvSetkAl654\",\"description\":\"YouTube — Meet a Google Researcher / Jiahui Yu interview\",\"timestamp\":1786930027280},{\"id\":\"f1339925-0548-4201-bb3f-ee3bdb7e5cef\",\"url\":\"https://www.linkedin.com/in/jhyuxm/\",\"description\":\"Jiahui Yu — LinkedIn\",\"timestamp\":1786930027280},{\"id\":\"416e1859-da11-4efc-a7cb-82f3ffb9ceaf\",\"url\":\"https://www.linkedin.com/in/jhyuxm/details/experience/\",\"description\":\"Jiahui Yu — LinkedIn Experience\",\"timestamp\":1786930027280},{\"id\":\"d272fc00-f48a-4006-bbd7-cc9bc46a700b\",\"url\":\"https://app.dealroom.co/news/note/jiahui-yu-leaves-meta-to-start-new-company-1\",\"description\":\"Dealroom — Jiahui Yu leaves Meta to start new company\",\"timestamp\":1786930027280},{\"id\":\"9089017f-1563-43f8-9c24-3cc9159a1c35\",\"url\":\"https://finance.biggo.com/news/9e5b9e02-0fe3-4702-9782-2265f2e5935d\",\"description\":\"BigGo Finance — Meta core AI researcher Jiahui Yu departs to launch startup\",\"timestamp\":1786930027281},{\"id\":\"647113e8-4af6-4ac2-9ecd-0e86de4cae17\",\"url\":\"https://eu.36kr.com/en/p/3938796537183367\",\"description\":\"36Kr — Jiahui Yu resigned from Meta to start his own business\",\"timestamp\":1786930027281},{\"id\":\"0c86fd0e-1b8e-4fea-8b25-740579aff3bf\",\"url\":\"https://www.webull.ca/news-detail/15401903810487296\",\"description\":\"Webull / Benzinga — Ex-Gemini, GPT-4o Researcher Jiahui Yu Leaves Meta To Found AI Startup\",\"timestamp\":1786930027281},{\"id\":\"e7ea5506-41c7-4717-97e8-42453956aec0\",\"url\":\"https://x.com/jiahuiyu/status/2087936732939616299\",\"description\":\"Jiahui Yu — announcement on X\",\"timestamp\":1786930027281}]"},{"id":"website","value":"https://jiahuiyu.com/"},{"id":"linkedin_profile","value":"https://www.linkedin.com/in/jhyuxm/"},{"id":"twitter_profile","value":"https://x.com/jhyuxm"},{"id":"previous_cid","value":"\"https://ipfs.everipedia.org/ipfs/QmSL2iy3z9aJekZFStau2qZVtR47jkDBcG2BKcpoTnZfPL\""},{"id":"commit-message","value":"\"Updated wiki: removed Perception/OpenAI and Gemini Multimodal/DeepMind line; added ..; tags -> Developer; category -> People in crypto; added 5 refs\""},{"id":"previous_cid","value":"QmSL2iy3z9aJekZFStau2qZVtR47jkDBcG2BKcpoTnZfPL"}],"events":[],"user":{"id":"0x8af7a19a26d8fbc48defb35aefb15ec8c407f889"},"author":{"id":"0x8AF7a19a26d8FBC48dEfB35AEfb15Ec8c407f889"},"operator":{"id":"0x1E23b34d3106F0C1c74D17f2Cd0F65cdb039b138"},"language":"en","version":1,"linkedWikis":{"blockchains":[],"founders":[],"speakers":[]},"recentActivity":"{\"items\":[{\"id\":\"a913dbaf-7ce0-4901-8e24-f76b4b621f2d\",\"title\":\"Jiahui Yu\",\"description\":\"Jiahui Yu is an AI researcher known for his work on deep learning and high-performance computing. He is a member of Meta's Superintelligence Labs and previously...\",\"timestamp\":\"2026-08-17T01:37:07.762Z\",\"category\":\"People in crypto\",\"status\":{\"icon\":\"RiGlobalLine\",\"label\":\"Wiki Updated\",\"iconClassName\":\"text-green-500\"},\"user\":{\"name\":\"0x8AF7a19a26d8FBC48dEfB35AEfb15Ec8c407f889\",\"address\":\"0x1E23b34d3106F0C1c74D17f2Cd0F65cdb039b138\"},\"button\":{\"label\":\"View Summary\",\"icon\":\"RiFileTextLine\"},\"summarySections\":[{\"title\":\"Title\",\"subtitle\":\"Changed the wiki title\",\"variant\":\"modified\",\"changeCount\":1,\"changes\":[\"Changed title from \\\"people\\\" to \\\"People in crypto\\\"\"]},{\"title\":\"Content\",\"subtitle\":\"Replaced and updated the main article content: lead paragraph rewritten, multiple career sections updated/expanded, new 'New Company' material added, and interview mention retained\",\"variant\":\"modified\",\"changeCount\":9,\"changes\":[\"Lead/Introduction: Rewrote lead to describe Jiahui Yu as an \\\"artificial intelligence researcher and entrepreneur\\\", note he co-founded TBD Lab within Meta Superintelligence Labs, led perception research at OpenAI, co-led the multimodal component of Google's Gemini project at Google DeepMind, and announced departure from Meta to start a new company in August 2026 [[7]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b) [[8]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35)\",\"Education section: Rewrote/clarified education details to state BS from University of Science and Technology of China and PhD from University of Illinois Urbana-Champaign with research focus on deep learning, computer vision, and efficient neural networks [[1]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)\",\"Career (early internships/consulting): Streamlined timeline of internships and consulting roles (Microsoft Research Asia; Megvii Research; Jump Trading; Adobe Research; Snap Research; Baidu; Nvidia; Google Brain), with citations included in the new text [[1]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) [[6]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf)\",\"Google and Google DeepMind subsection: Added/expanded text stating Yu joined Google in Feb 2020, worked on speech recognition, multimodal representation and generative models, became senior research scientist, then co-led the multimodal pillar of Gemini at Google DeepMind and left DeepMind in 2023 [[1]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) [[6]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf)\",\"OpenAI subsection: Added details about Yu joining OpenAI in Oct 2023 to lead the Perception team and lists contributions to GPT-4o (data/encoders/pre- and post-training), Thinking with Images, o3 and o4-mini [[1]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) [[6]](#cite-id-416e1859-da11-4efc-a7cb-82f3ffb9ceaf)\",\"Meta Superintelligence Labs and TBD Lab: Added/expanded section describing Meta's Superintelligence Labs (MSL) organization and Yu joining Meta in 2025, co-founding TBD Lab, leading multimodal work (Muse Spark, Muse Image, Muse Video), and leaving Meta in August 2026; section citations span MSL and TBD Lab references [[2]](#cite-id-df9f59f1-2422-4e3e-9951-cd21dc1947df) [[3]](#cite-id-fb95d7db-dcbb-4821-97a4-b691303930f0) [[1]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c) [[8]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35) [[9]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17) [[7]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b)\",\"New Company: Added a new subsection reporting Yu's August 2026 announcement that he left Meta to start a new company, with statements he has not publicly disclosed details; includes multiple supporting references [[7]](#cite-id-d272fc00-f48a-4006-bbd7-cc9bc46a700b) [[8]](#cite-id-9089017f-1563-43f8-9c24-3cc9159a1c35) [[9]](#cite-id-647113e8-4af6-4ac2-9ecd-0e86de4cae17) [[10]](#cite-id-0c86fd0e-1b8e-4fea-8b25-740579aff3bf) [[11]](#cite-id-e7ea5506-41c7-4717-97e8-42453956aec0)\",\"Selected Work: Added/updated a bulleted list of major multimodal and foundation-model projects (Muse Spark 1.0/1.1/1.2; Muse Image; Muse Video; Thinking with Images; o3; o4-mini; GPT-4o contributions; Gemini) and appended relevant citation [[1]](#cite-id-ade53904-907e-4867-b1fb-4c1cf9fc234c)\",\"Interviews: Retained and reworded interview mention about Google's Meet a Google Researcher (Parti discussion) and preserved the YouTube link at the end of the article [[4]](#cite-id-75747682-590a-40bb-bb90-a56a9941c73e)\"]},{\"title\":\"References\",\"subtitle\":\"Replaced the references list with an updated set of reference entries\",\"variant\":\"modified\",\"changeCount\":12,\"changes\":[\"Removed old reference entries (ids: h7hLdBmFI7, Ndxvn8Agjy, TGGQ8858kD, 4qk74CgzJG, dnCDcKgWVt, xnkW5DqTSW)\",\"Added reference: \\\"Jiahui Yu — Personal Website\\\" (id: ade53904-907e-4867-b1fb-4c1cf9fc234c, url: https://jiahuiyu.com/)\",\"Added reference: \\\"CNBC — Mark Zuckerberg creating Meta Superintelligence Labs: read the memo\\\" (id: df9f59f1-2422-4e3e-9951-cd21dc1947df, url: https://www.cnbc.com/2025/06/30/mark-zuckerberg-creating-meta-superintelligence-labs-read-the-memo.html)\",\"Added reference: \\\"Reuters — Meta deepens AI push with 'Superintelligence' lab\\\" (id: fb95d7db-dcbb-4821-97a4-b691303930f0, url: https://www.reuters.com/business/meta-deepens-ai-push-with-superintelligence-lab-source-says-2025-06-30/)\",\"Added reference: \\\"YouTube — Meet a Google Researcher / Jiahui Yu interview\\\" (id: 75747682-590a-40bb-bb90-a56a9941c73e, url: https://www.youtube.com/watch?v=hvSetkAl654)\",\"Added reference: \\\"Jiahui Yu — LinkedIn\\\" (id: f1339925-0548-4201-bb3f-ee3bdb7e5cef, url: https://www.linkedin.com/in/jhyuxm/)\",\"Added reference: \\\"Jiahui Yu — LinkedIn Experience\\\" (id: 416e1859-da11-4efc-a7cb-82f3ffb9ceaf, url: https://www.linkedin.com/in/jhyuxm/details/experience/)\",\"Added reference: \\\"Dealroom — Jiahui Yu leaves Meta to start new company\\\" (id: d272fc00-f48a-4006-bbd7-cc9bc46a700b, url: https://app.dealroom.co/news/note/jiahui-yu-leaves-meta-to-start-new-company-1)\",\"Added reference: \\\"BigGo Finance — Meta core AI researcher Jiahui Yu departs to launch startup\\\" (id: 9089017f-1563-43f8-9c24-3cc9159a1c35, url: https://finance.biggo.com/news/9e5b9e02-0fe3-4702-9782-2265f2e5935d)\",\"Added reference: \\\"36Kr — Jiahui Yu resigned from Meta to start his own business\\\" (id: 647113e8-4af6-4ac2-9ecd-0e86de4cae17, url: https://eu.36kr.com/en/p/3938796537183367)\",\"Added reference: \\\"Webull / Benzinga — Ex-Gemini, GPT-4o Researcher Jiahui Yu Leaves Meta To Found AI Startup\\\" (id: 0c86fd0e-1b8e-4fea-8b25-740579aff3bf, url: https://www.webull.ca/news-detail/15401903810487296)\",\"Added reference: \\\"Jiahui Yu — announcement on X\\\" (id: e7ea5506-41c7-4717-97e8-42453956aec0, url: https://x.com/jiahuiyu/status/2087936732939616299)\"]},{\"title\":\"Summary\",\"subtitle\":\"Updated the article summary text\",\"variant\":\"modified\",\"changeCount\":2,\"changes\":[\"Previous summary: \\\"Jiahui Yu is an AI researcher known for his work on deep learning and high-performance computing. He is a member of Meta's Superintelligence Labs and previously led the Perception team at OpenAI and co-led Gemini Multimodal at Google DeepMind.\\\"\",\"New summary: \\\"Jiahui Yu is an AI researcher known for his work on deep learning and high-performance computing. He is a member of Meta's Superintelligence Labs and previously...\\\"\"]},{\"title\":\"Tags\",\"subtitle\":\"Removed several tags and added new tags (including tag-like metadata entries and a revised tags array)\",\"variant\":\"modified\",\"changeCount\":10,\"changes\":[\"Removed tag: \\\"AI\\\"\",\"Removed tag: \\\"PeopleInDeFi\\\"\",\"Removed tag: \\\"Developers\\\"\",\"Removed tag: \\\"Organizations\\\"\",\"Added tag: \\\"AI Token\\\"\",\"Added tag: \\\"Developer\\\"\",\"Added tag-like metadata entry: id \\\"words-changed\\\" with value \\\"1\\\"\",\"Added tag-like metadata entry: id \\\"percent-changed\\\" with value \\\"0.02\\\"\",\"Added tag-like metadata entry: id \\\"blocks-changed\\\" with value \\\"content, tags, summary\\\"\",\"Added tag-like metadata entry: id \\\"wiki-score\\\" with value \\\"65\\\"\"]},{\"title\":\"Media / Video entry\",\"subtitle\":\"Updated video/media object properties (removed some fields, added others)\",\"variant\":\"modified\",\"changeCount\":5,\"changes\":[\"Removed property: \\\"speakers\\\": []\",\"Removed property: \\\"caption\\\": \\\"\\\"\",\"Removed property: \\\"thumbnail\\\": \\\"https://www.youtube.com/watch?v=hvSetkAl654\\\"\",\"Added property: \\\"size\\\": null\",\"Added property: \\\"type\\\": null\"]}]}]}"}