{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T16:33:20.284Z","data":{"id":"brf_vvsvw70dLdTi","kind":"daily","slug":"2026-10-09","window":{"from":"2026-10-09T00:00:00.000Z","to":"2026-10-10T00:00:00.000Z"},"version":1,"quiet":false,"title":"AI brief · 9 October 2026","headline":{"text":"Turn documents, charts, audio, and video into structured information","recordIds":["wsa_7a8daa96gh9j"]},"dek":{"text":"Youtu-Parsing-Omni turns documents, images, charts, audio, and video into structured information such as text, tables, transcripts, and reports. Antalia-2 Mini offers a local option for turning Turkish text into speech, with model weights and code available under Apache-2.0. Project Maya has three compact versions of GLM-5.3-Flash for local use; their memory needs and reported accuracy differ. Darwin-27B-ZTC-v2 scores choices and yes-or-no questions without generating text, which could suit decision steps in a workflow. Qwen-Image-2.1-Turbo is a checkpoint for generating and editing images with Diffusers.","recordIds":["wsa_7a8daa96gh9j","wsa_xa5s9uuttpjn","wsa_sj5z83a2eaxv","wsa_4afvy3iircbh","wsa_d8hpqx95w4w5","wsa_zwjdvrdbpq2n","wsa_aiqrvg2q8um2"]},"tldr":[{"text":"Youtu-Parsing-Omni turns documents, images, charts, audio, and video into structured information such as text, tables, transcripts, and reports.","recordIds":["wsa_7a8daa96gh9j"]},{"text":"Antalia-2 Mini offers a local option for turning Turkish text into speech, with model weights and code available under Apache-2.0.","recordIds":["wsa_xa5s9uuttpjn"]},{"text":"Project Maya has three compact versions of GLM-5.3-Flash for local use; their memory needs and reported accuracy differ.","recordIds":["wsa_sj5z83a2eaxv","wsa_4afvy3iircbh","wsa_d8hpqx95w4w5"]},{"text":"Darwin-27B-ZTC-v2 scores choices and yes-or-no questions without generating text, which could suit decision steps in a workflow.","recordIds":["wsa_zwjdvrdbpq2n"]},{"text":"Qwen-Image-2.1-Turbo is a checkpoint for generating and editing images with Diffusers.","recordIds":["wsa_aiqrvg2q8um2"]}],"stories":[{"blocks":[{"kind":"paragraph","items":[{"text":"**Youtu-Parsing-Omni** accepts documents, images, charts, geometry figures, audio, and video, then produces structured JSON based on the task prompt.","recordIds":["wsa_7a8daa96gh9j"]},{"text":"That output can include text, tables, captions, transcripts, or reports, making the model relevant to people building tools that need to extract information from different kinds of media.","recordIds":["wsa_7a8daa96gh9j"]}]}],"heading":"Turn documents, charts, audio, and video into structured information"},{"blocks":[{"kind":"paragraph","items":[{"text":"**Antalia-2 Mini** is a small text-to-speech model that produces Turkish speech in one synthetic male voice.","recordIds":["wsa_xa5s9uuttpjn"]},{"text":"It includes Turkish text normalization and can be used locally through Python or a command-line interface; its weights and code are released under Apache-2.0.","recordIds":["wsa_xa5s9uuttpjn"]}]}],"heading":"Generate Turkish speech locally from text"},{"blocks":[{"kind":"paragraph","items":[{"text":"Project Maya has released three quantizations of **GLM-5.3-Flash** for computers with limited combined RAM and GPU memory.","recordIds":["wsa_sj5z83a2eaxv","wsa_4afvy3iircbh","wsa_d8hpqx95w4w5"]},{"text":"**Maya-S** is reported to retain 97.9% of the full model’s accuracy on the listed zero-shot tasks, while **Maya-L** is reported to retain 99.2% and pick the same next token 90% of the time.","recordIds":["wsa_d8hpqx95w4w5","wsa_sj5z83a2eaxv"]},{"text":"**Maya-S24** is reported to use about 1.5 GB less GPU memory than Maya-S and decode 14% faster in a benchmark on one 24 GB Tesla V100.","recordIds":["wsa_4afvy3iircbh"]}]},{"kind":"list","items":[{"text":"Maya-S: 96.5 GB.","recordIds":["wsa_d8hpqx95w4w5"]},{"text":"Maya-S24: 94.7 GB.","recordIds":["wsa_4afvy3iircbh"]},{"text":"Maya-L: 156.3 GB.","recordIds":["wsa_sj5z83a2eaxv"]}]}],"heading":"Three local versions of GLM-5.3-Flash trade memory needs against reported accuracy"},{"blocks":[{"kind":"paragraph","items":[{"text":"**Darwin-27B-ZTC-v2** takes a state and a typed question, then returns probabilities for the available options in one pass without generating tokens.","recordIds":["wsa_zwjdvrdbpq2n"]},{"text":"It can score yes-or-no decisions, choose among labels, or rate options against an ordered set of criteria—for example, as one step in a control or workflow decision.","recordIds":["wsa_zwjdvrdbpq2n"]}]}],"heading":"A model that scores decisions without generating text"},{"blocks":[{"kind":"paragraph","items":[{"text":"**Qwen-Image-2.1-Turbo** is an accelerated checkpoint for generating images from text prompts and editing images.","recordIds":["wsa_aiqrvg2q8um2"]},{"text":"It uses the same 7B visual generation architecture as Qwen-Image-2.1 and loads with the Diffusers QwenImage21Pipeline.","recordIds":["wsa_aiqrvg2q8um2"]}]}],"heading":"Generate and edit images with Qwen-Image-2.1-Turbo"}],"radar":[{"text":"**Amazon Bedrock Managed Agents** adds a setting that can return a human-readable summary of a model’s reasoning alongside its response.","recordIds":["wsa_7unr7rrrwvxq"]},{"text":"**Copilot code review** now has per-user settings and more detailed controls for automatic reviews, with an enterprise default review effort that organizations can inherit.","recordIds":["wsa_d7wg4ipxkash"]}],"sections":[{"heading":"Models","category":"model","recordIds":["wsa_sj5z83a2eaxv","wsa_4afvy3iircbh","wsa_d8hpqx95w4w5","wsa_xa5s9uuttpjn","wsa_7a8daa96gh9j","wsa_aiqrvg2q8um2","wsa_zwjdvrdbpq2n"],"sentences":[]},{"heading":"Developer platforms","category":"developer platform","recordIds":["wsa_7unr7rrrwvxq"],"sentences":[]},{"heading":"Applications","category":"application","recordIds":["wsa_itaxjsxj6uuk","wsa_d7wg4ipxkash","wsa_dis7u387rjzj","wsa_f9a7km9kjgi5"],"sentences":[]}],"items":[{"recordId":"wsa_sj5z83a2eaxv","versionId":"ver_QVtJBtWyr3wz","eventType":"new_development","category":"model","title":"Maya-L","maker":"mw00","summary":"Maya-L is Project Maya's 156.3 GB quantization of GLM-5.3-Flash, designed for computers with a large combined pool of RAM and GPU memory. The source reports that it retains 99.2% of the FP8 model's zero-shot accuracy and picks the same next token 90% of the time.","releaseNote":null,"classifications":{"developmentType":"model","capability":["text generation"],"modality":["text"],"access":["open weights"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["consumer","developer"]},"citations":[{"url":"https://github.com/mw00/project-maya","authority":"owner-controlled","publisher":"GitHub new repositories"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-06T22:55:13.000Z","effectiveAt":"2026-10-09T21:45:14.191Z","url":"https://wowsuchai.withglint.app/records/wsa_sj5z83a2eaxv","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_sj5z83a2eaxv","webUrl":"https://wowsuchai.withglint.app/records/wsa_sj5z83a2eaxv"},{"recordId":"wsa_4afvy3iircbh","versionId":"ver_hT1DV6jPZPnO","eventType":"new_development","category":"model","title":"Maya-S24","maker":"mw00","summary":"Maya-S24 is a 94.7 GB quantization of GLM-5.3-Flash with 2-bit routed experts and 4-bit attention and shared experts. The source reports that it uses about 1.5 GB less GPU memory than Maya-S and decodes 14% faster on one 24 GB Tesla V100 in its benchmark.","releaseNote":null,"classifications":{"developmentType":"model","capability":["text generation"],"modality":["text"],"access":["open weights"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["consumer","developer"]},"citations":[{"url":"https://github.com/mw00/project-maya","authority":"owner-controlled","publisher":"GitHub new repositories"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-06T22:55:13.000Z","effectiveAt":"2026-10-09T21:45:08.054Z","url":"https://wowsuchai.withglint.app/records/wsa_4afvy3iircbh","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_4afvy3iircbh","webUrl":"https://wowsuchai.withglint.app/records/wsa_4afvy3iircbh"},{"recordId":"wsa_d8hpqx95w4w5","versionId":"ver_7R93SWAYidFK","eventType":"new_development","category":"model","title":"Maya-S","maker":"mw00","summary":"Maya-S is Project Maya's 96.5 GB compact quantization of GLM-5.3-Flash, made for computers with a smaller pool of RAM and GPU memory. The source reports that it retains 97.9% of the full FP8 model's accuracy on the listed zero-shot tasks.","releaseNote":null,"classifications":{"developmentType":"model","capability":["text generation"],"modality":["text"],"access":["open weights"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["consumer","developer"]},"citations":[{"url":"https://github.com/mw00/project-maya","authority":"owner-controlled","publisher":"GitHub new repositories"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-06T22:55:13.000Z","effectiveAt":"2026-10-09T21:45:05.249Z","url":"https://wowsuchai.withglint.app/records/wsa_d8hpqx95w4w5","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_d8hpqx95w4w5","webUrl":"https://wowsuchai.withglint.app/records/wsa_d8hpqx95w4w5"},{"recordId":"wsa_xa5s9uuttpjn","versionId":"ver_ZqPVgYJm3AX0","eventType":"new_development","category":"model","title":"Antalia-2 Mini","maker":"cloud0day3","summary":"Antalia-2 Mini is a small Turkish text-to-speech model with one synthetic male voice and 7.62 million parameters. It produces 48 kHz audio, includes Turkish text normalization, and is released with model weights and code under Apache-2.0.","releaseNote":null,"classifications":{"developmentType":"model","capability":["audio generation"],"modality":["text","audio"],"access":["web","SDK","CLI","open weights"],"deployment":["on-device"],"pricing":["free","open-source"],"targetUser":["developer","creator"]},"citations":[{"url":"https://huggingface.co/cloud0day3/antalia-mini","authority":"owner-controlled","publisher":"Hugging Face"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-08T10:57:38.000Z","effectiveAt":"2026-10-09T15:42:43.427Z","url":"https://wowsuchai.withglint.app/records/wsa_xa5s9uuttpjn","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_xa5s9uuttpjn","webUrl":"https://wowsuchai.withglint.app/records/wsa_xa5s9uuttpjn"},{"recordId":"wsa_7a8daa96gh9j","versionId":"ver_0RfPxHv8KWlr","eventType":"new_development","category":"model","title":"Youtu-Parsing-Omni","maker":"Tencent Hunyuan","summary":"Youtu-Parsing-Omni is a 5B omni-modal parsing model that accepts documents, images, charts, geometry figures, audio, and video. It produces structured JSON covering perception and cognition tasks, with outputs selected by a task prompt.","releaseNote":null,"classifications":{"developmentType":"model","capability":["extraction","analysis"],"modality":["text","image","audio","video","multimodal"],"access":["open weights","CLI"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["developer","researcher","enterprise"]},"citations":[{"url":"https://huggingface.co/tencent/Youtu-Parsing-Omni","authority":"owner-controlled","publisher":"Tencent Hunyuan"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-09T06:42:18.000Z","effectiveAt":"2026-10-09T15:42:36.032Z","url":"https://wowsuchai.withglint.app/records/wsa_7a8daa96gh9j","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_7a8daa96gh9j","webUrl":"https://wowsuchai.withglint.app/records/wsa_7a8daa96gh9j"},{"recordId":"wsa_aiqrvg2q8um2","versionId":"ver_TcuEIdHBWsCD","eventType":"new_development","category":"model","title":"Qwen-Image-2.1-Turbo","maker":"Alibaba Qwen","summary":"Qwen-Image-2.1-Turbo is an accelerated checkpoint for text-to-image generation and image editing. It uses the same 7B visual generation architecture as Qwen-Image-2.1 and loads with the Diffusers QwenImage21Pipeline.","releaseNote":null,"classifications":{"developmentType":"model","capability":["image generation"],"modality":["text","image"],"access":["SDK","open weights"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["developer","creator"]},"citations":[{"url":"https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo","authority":"owner-controlled","publisher":"Hugging Face"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-09T04:50:01.000Z","effectiveAt":"2026-10-09T15:42:33.150Z","url":"https://wowsuchai.withglint.app/records/wsa_aiqrvg2q8um2","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_aiqrvg2q8um2","webUrl":"https://wowsuchai.withglint.app/records/wsa_aiqrvg2q8um2"},{"recordId":"wsa_zwjdvrdbpq2n","versionId":"ver_q-jfh3OEEWFE","eventType":"new_development","category":"model","title":"Darwin-27B-ZTC-v2","maker":"FINAL-Bench","summary":"Darwin-27B-ZTC-v2 is a zero-token decision model that takes a state and a typed question and returns probabilities for each option. It uses one forward pass per question and generates no tokens.","releaseNote":null,"classifications":{"developmentType":"model","capability":["analysis","text generation"],"modality":["text"],"access":["open weights","API"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["developer","researcher","enterprise"]},"citations":[{"url":"https://huggingface.co/FINAL-Bench/Darwin-27B-ZTC-v2","authority":"owner-controlled","publisher":"Hugging Face"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-08T15:28:29.000Z","effectiveAt":"2026-10-09T03:39:01.770Z","url":"https://wowsuchai.withglint.app/records/wsa_zwjdvrdbpq2n","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_zwjdvrdbpq2n","webUrl":"https://wowsuchai.withglint.app/records/wsa_zwjdvrdbpq2n"},{"recordId":"wsa_7unr7rrrwvxq","versionId":"ver_eZsLogEpxiKf","eventType":"major_release","category":"developer platform","title":"Amazon Bedrock Managed Agents","maker":"AWS","summary":"Amazon Bedrock Managed Agents is built on a customized version of OpenAI's Agents API and integrated with AWS resources. It manages agent state, tool use, code execution, and multi-step coordination, with durable sessions, reusable skills, and support for MCP servers.","releaseNote":"Adds support for the reasoning.summary parameter for OpenAI models through the Responses API, returning a human-readable reasoning summary alongside the model response.","classifications":{"developmentType":"developer platform","capability":["agents","automation","text generation","analysis"],"modality":["text"],"access":["API"],"deployment":["hosted"],"pricing":["free","usage-based","unknown"],"targetUser":["developer","enterprise"]},"citations":[{"url":"https://aws.amazon.com/about-aws/whats-new/2026/09/bedrock-managed-agents-preview/","authority":"owner-controlled","publisher":"AWS"},{"url":"https://aws.amazon.com/about-aws/whats-new/2026/09/claude-region-expansion-in-sk/","authority":"owner-controlled","publisher":"AWS"},{"url":"https://aws.amazon.com/about-aws/whats-new/2026/10/amazon-bedrock-reasoning-summaries-openai/","authority":"owner-controlled","publisher":"AWS"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-09-29T21:10:00.000Z","effectiveAt":"2026-10-09T21:44:33.180Z","url":"https://wowsuchai.withglint.app/records/wsa_7unr7rrrwvxq","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_7unr7rrrwvxq","webUrl":"https://wowsuchai.withglint.app/records/wsa_7unr7rrrwvxq"},{"recordId":"wsa_itaxjsxj6uuk","versionId":"ver_gaGOXOY1dT3t","eventType":"major_release","category":"application","title":"Amazon Connect Customer","maker":"AWS","summary":"Amazon Connect Customer now supports agent-to-agent collaboration, allowing specialized AI agents to be brought into a live customer interaction. The launch expands the open A2A protocol to support voice streaming and interaction-level session continuity and provides unified observability, guardrails, and escalation controls across collaborating agents.","releaseNote":"Adds a one-click automated check that compares evaluation forms with best practices and suggests ways to make questions more specific for reliable AI scoring.","classifications":{"developmentType":"application","capability":["agents","automation","audio generation","search","analysis","retrieval"],"modality":["text","audio","multimodal"],"access":["web","API","SDK"],"deployment":["hosted"],"pricing":["unknown"],"targetUser":["enterprise","developer"]},"citations":[{"url":"https://aws.amazon.com/about-aws/whats-new/2026/09/Amazon-Connect-Customer-A2A","authority":"owner-controlled","publisher":"AWS"},{"url":"https://aws.amazon.com/about-aws/whats-new/2026/09/connect-customer-custom-metrics-apis/","authority":"owner-controlled","publisher":"AWS"},{"url":"https://aws.amazon.com/about-aws/whats-new/2026/10/amazon-connect-customer-automated-checks-evaluation-forms/","authority":"owner-controlled","publisher":"AWS"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-09-22T04:00:00.000Z","effectiveAt":"2026-10-09T21:44:36.104Z","url":"https://wowsuchai.withglint.app/records/wsa_itaxjsxj6uuk","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_itaxjsxj6uuk","webUrl":"https://wowsuchai.withglint.app/records/wsa_itaxjsxj6uuk"},{"recordId":"wsa_d7wg4ipxkash","versionId":"ver_qWA2s6wr5b-C","eventType":"major_release","category":"application","title":"Copilot code review","maker":"GitHub","summary":"Copilot code review adds a dedicated per-user settings page and more granular automatic-review controls, plus an enterprise-level default review effort that can be inherited by organizations. These changes are generally available across Copilot plans including Business and Enterprise.","releaseNote":"Adds organization billing options and controls for who can request a review.","classifications":{"developmentType":"application","capability":["analysis","automation","agents","code generation","safety","extraction"],"modality":["code","text"],"access":["web","desktop","API","CLI"],"deployment":["hosted","on-device"],"pricing":["subscription","unknown","usage-based"],"targetUser":["developer","enterprise"]},"citations":[{"url":"https://github.blog/changelog/2026-09-23-copilot-code-review-more-ways-to-request-and-configure-reviews","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-09-24-default-enablement-of-copilot-features-for-copilot-business-and-enterprise","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-09-25-enterprise-managed-settings-in-product-validator","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-09-30-hydrafusion-in-vs-code-and-the-github-copilot-app","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-10-02-copilot-code-review-api-support-and-new-default-effort-level","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-10-02-github-copilot-weekly-releases-september-28","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-10-07-local-sandboxing-for-github-copilot-now-generally-available","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-10-07-purpose-built-model-for-leaked-secret-detection","authority":"owner-controlled","publisher":"GitHub"},{"url":"https://github.blog/changelog/2026-10-08-copilot-code-review-new-organization-billing-options-and-controls","authority":"owner-controlled","publisher":"GitHub"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-09-23T21:25:58.000Z","effectiveAt":"2026-10-09T21:44:30.552Z","url":"https://wowsuchai.withglint.app/records/wsa_d7wg4ipxkash","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_d7wg4ipxkash","webUrl":"https://wowsuchai.withglint.app/records/wsa_d7wg4ipxkash"},{"recordId":"wsa_dis7u387rjzj","versionId":"ver_S_Ic2nQvmurS","eventType":"new_development","category":"application","title":"Brewery","maker":"Empero","summary":"Brewery is a guided console agent for fine-tuning language and image models. It guides users through model and data selection, training, testing, export, and publishing.","releaseNote":null,"classifications":{"developmentType":"application","capability":["fine-tuning","agents","automation","training"],"modality":["text","image"],"access":["CLI"],"deployment":["on-premises"],"pricing":["unknown"],"targetUser":["developer","researcher","creator"]},"citations":[{"url":"https://github.com/empero-org/brewery-ai","authority":"owner-controlled","publisher":"GitHub new repositories"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-04T22:16:28.000Z","effectiveAt":"2026-10-09T15:42:50.473Z","url":"https://wowsuchai.withglint.app/records/wsa_dis7u387rjzj","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_dis7u387rjzj","webUrl":"https://wowsuchai.withglint.app/records/wsa_dis7u387rjzj"},{"recordId":"wsa_f9a7km9kjgi5","versionId":"ver__AWYW5HYuk2z","eventType":"new_development","category":"application","title":"RoboHarness","maker":"BinceQu","summary":"RoboHarness is an open-source robotic control harness that lets LLM agents operate embodied tasks using visual clicks, tracked keypoints, and geometric constraints. It includes a robot interface, task runner, and evaluation pipeline for the BEHAVIOR simulator.","releaseNote":null,"classifications":{"developmentType":"application","capability":["agents","automation"],"modality":["text","image"],"access":["CLI"],"deployment":["on-premises"],"pricing":["open-source"],"targetUser":["developer","researcher"]},"citations":[{"url":"https://github.com/BinceQu/RoboHarness","authority":"owner-controlled","publisher":"GitHub new repositories"}],"score":1,"confidence":"high","correctionState":"current","publishedAt":"2026-10-07T04:39:45.000Z","effectiveAt":"2026-10-09T15:42:49.233Z","url":"https://wowsuchai.withglint.app/records/wsa_f9a7km9kjgi5","apiUrl":"https://wowsuchai.withglint.app/api/v1/records/wsa_f9a7km9kjgi5","webUrl":"https://wowsuchai.withglint.app/records/wsa_f9a7km9kjgi5"}],"corrections":[],"notes":[],"writer":{"kind":"model","model":"openai/gpt-6-luna"},"publishedAt":"2026-10-10T00:41:07.997Z","updatedAt":"2026-10-10T00:41:07.997Z","url":"https://wowsuchai.withglint.app/briefs/daily/2026-10-09","apiUrl":"https://wowsuchai.withglint.app/api/v1/briefs/daily/2026-10-09"},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}