{"id":"61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d","title":"Lenny's Newsletter: Claire Vo’s first look at Meta’s Muse Wonder","argument":"In Lenny's Newsletter, Claire Vo reports testing Meta’s Muse Wonder and Wonder Full on nearly 20 tasks in the How I AI bench, spanning prototyping, agentic workflows, coding, writing, and creative work. She says the results partly support Meta’s framing of Muse as a “personal and professional agent,” while identifying limits.\n\nVo scored the tasks with an LLM-as-a-judge pass and her own voice notes. Her overview says Muse ranked first on three agentic tasks, but the supplied page does not identify those tasks or give detailed scores. It also flags weak design output and compares Muse with other models on SVG illustration and short-form video.\n\nThe practical question in Vo’s account is where the model’s strengths translate into work she would actually use: the episode also examines email writing, voice-assistant tasks, and whether she will add Muse to her agent workflows. The available page lists those subjects but does not include the detailed results or her final workflow decision. Escape Meridian interpretation: this first-look account of one person’s bench does not establish performance across users or real-world tasks.","topicIds":["work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The supplied page contains an episode description and topic outline, not the detailed results, scores, or full discussion. The page does not identify the three agentic tasks where Muse ranked first or state Vo’s final decision about using it in her workflows.","speaker":{"name":"Claire Vo","roleAtSource":"Article author"},"source":{"title":"Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design","publisher":"Lenny's Newsletter","format":"Article","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","publishedAt":"2026-10-14T12:04:05+00:00","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Claire Vo says she tested Meta’s Muse Wonder and Wonder Full on nearly 20 tasks across several kinds of work.","excerpt":"I put Meta’s new Muse Wonder (and Wonder Full) frontier models through the How I AI bench, which covers nearly 20 tasks across prototyping, agentic workflows, coding, writing, and creative work.","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Source-stated"},{"text":"Vo says she used an LLM-as-a-judge pass and her own voice notes to score the tasks.","excerpt":"I scored everything with an LLM-as-a-judge pass and my own voice notes","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Source-stated"},{"text":"The episode outline says Muse ranked first on three agentic tasks, but the supplied page does not name them.","excerpt":"The three agentic tasks where Muse ranked first, and why those categories matter","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Source-stated"},{"text":"The page presents Vo’s assessment as a first look, not a broad evaluation across users or real-world tasks.","excerpt":"then pulled together the first-look results you see here.","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","checkedAt":"2026-11-05T04:10:49.352Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=dChiPsd0uF4","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/2f168491-8e02-4135-9c6b-a9966afc9613_1456x1048.png","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Which agentic tasks did Muse rank first on, and what did Vo conclude about using it in her own workflows?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Lenny's Newsletter: Claire Vo’s first look at Meta’s Muse Wonder","summary":"In Lenny's Newsletter, Claire Vo reports testing Meta’s Muse Wonder and Wonder Full on nearly 20 tasks in the How I AI bench, spanning prototyping, agentic workflows, coding, writing, and creative work. She says the results partly support Meta’s framing of Muse as a “personal and professional agent,” while identifying limits.\n\nVo scored the tasks with an LLM-as-a-judge pass and her own voice notes. Her overview says Muse ranked first on three agentic tasks, but the supplied page does not identify those tasks or give detailed scores. It also flags weak design output and compares Muse with other models on SVG illustration and short-form video.\n\nThe practical question in Vo’s account is where the model’s strengths translate into work she would actually use: the episode also examines email writing, voice-assistant tasks, and whether she will add Muse to her agent workflows. The available page lists those subjects but does not include the detailed results or her final workflow decision. Escape Meridian interpretation: this first-look account of one person’s bench does not establish performance across users or real-world tasks.","question":"Which agentic tasks did Muse rank first on, and what did Vo conclude about using it in her own workflows?","claims":[{"text":"Claire Vo says she tested Meta’s Muse Wonder and Wonder Full on nearly 20 tasks across several kinds of work.","excerpt":"I put Meta’s new Muse Wonder (and Wonder Full) frontier models through the How I AI bench, which covers nearly 20 tasks across prototyping, agentic workflows, coding, writing, and creative work.","support":"source-stated"},{"text":"Vo says she used an LLM-as-a-judge pass and her own voice notes to score the tasks.","excerpt":"I scored everything with an LLM-as-a-judge pass and my own voice notes","support":"source-stated"},{"text":"The episode outline says Muse ranked first on three agentic tasks, but the supplied page does not name them.","excerpt":"The three agentic tasks where Muse ranked first, and why those categories matter","support":"source-stated"},{"text":"The page presents Vo’s assessment as a first look, not a broad evaluation across users or real-world tasks.","excerpt":"then pulled together the first-look results you see here.","support":"interpretation"}],"limitations":["The supplied page contains an episode description and topic outline, not the detailed results, scores, or full discussion.","The page does not identify the three agentic tasks where Muse ranked first or state Vo’s final decision about using it in her workflows."],"mediaId":"388004979cb49712b4d7ec4b2d7f649f8fcf890b1928914b3205afbdc79838c0","correctionReason":null,"id":"61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d","publicationId":"cdea8f8f-f31a-4964-896e-41fe517174c1","version":1,"sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","sourceTitle":"Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design","publisher":"Lenny's Newsletter","publishedAt":"2026-10-14T12:04:05+00:00","originalPublished":{"value":"2026-10-14T12:04:05+00:00","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-04T12:36:44.834Z","createdAt":"2026-11-05T04:23:19.470Z","historical":true,"entityIds":["lennys-newsletter"],"topicIds":["work-and-agency"],"media":[{"id":"388004979cb49712b4d7ec4b2d7f649f8fcf890b1928914b3205afbdc79838c0","kind":"article","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-05T04:10:49.500Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"d2f660cd4d16b5af98d8913e4bfa6dd1cc5d3505a1b07ca0d13a3e26fdc5b7c4","kind":"video","url":"https://www.youtube.com/watch?v=dChiPsd0uF4","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","label":"Watch source","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-05T04:10:49.500Z","method":"publisher_association_and_head","contentType":"text/html","cacheUntil":1793851849500},"recommendationReason":"Observed on the acquired publisher source; availability checked."},{"id":"b6af37784a72cf56cc3a5c43f5c6686323e56e26ebc70a0c02c2382aab4b446e","kind":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/2f168491-8e02-4135-9c6b-a9966afc9613_1456x1048.png","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-05T04:10:49.500Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1793852149500},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","checkedAt":"2026-11-05T04:10:49.352Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=dChiPsd0uF4","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/2f168491-8e02-4135-9c6b-a9966afc9613_1456x1048.png","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"editorialDecision":{"outcome":"accept","reasonCodes":["useful_perspective"],"rubricVersion":"stream-admission-v5","mediaId":"388004979cb49712b4d7ec4b2d7f649f8fcf890b1928914b3205afbdc79838c0","confidence":0.8799999999999999,"provider":"typesafe","model":"jev-1.13.0","inputHash":"116eb45f45f814e23a2900aa35d306843548150edff142aaedae3b26ca96000c","decidedAt":"2026-11-05T04:10:50.784Z"},"provenance":{"textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observationId":"e2794b5c36a0e146795ade6b93cbf45f3e7fbe481f768c7451084a666de74f4c","retrievedAt":"2026-11-05T04:10:49.352Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"b3c8e596-cd25-425a-88fa-cd19df2873bd"},"reviewer":{"model":"gpt-6-luna","runId":"bc12903f-669e-41a7-85f8-89e5f4889d3e"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-05T04:23:19.470Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23484.author"},"assertionId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T04:10:49.352Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z"}},{"actor":{"name":"Claire Vo","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","locator":"head/meta[name=author|citation_author]"},"assertionId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T04:10:49.352Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z"}},{"actor":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/","kind":"unknown","actorId":null},"role":"publisher","scope":{"kind":"publication","locator":null},"literalCredit":"Lenny's Newsletter","status":"stated","provenance":{"basis":"article-publisher","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23484.publisher"},"assertionId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T04:10:49.352Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/"},"sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z","basis":"publisher-page-metadata","sourceLinks":52,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d/source"}},"canonicalUrl":"https://escapemeridian.com/readings/lenny-s-newsletter-claire-vo-s-first-look-at-meta-s-muse-wonder-61d83e4b","formats":{"html":"/readings/lenny-s-newsletter-claire-vo-s-first-look-at-meta-s-muse-wonder-61d83e4b","markdown":"/readings/lenny-s-newsletter-claire-vo-s-first-look-at-meta-s-muse-wonder-61d83e4b.md","json":"/readings/lenny-s-newsletter-claire-vo-s-first-look-at-meta-s-muse-wonder-61d83e4b.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-agentic","name":"Agentic AI","explanation":"AI systems that plan and carry out a series of steps toward a goal, often by using other software, rather than giving one answer.","referenceUrl":"https://developers.google.com/machine-learning/glossary#agentic"},{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"}],"entities":[{"id":"lennys-newsletter","name":"Lenny's Newsletter","kind":"organization","context":"Lenny's Newsletter is Lenny Rachitsky's publication and podcast on product management, growth and career questions for product people.","referenceUrls":["https://www.lennysnewsletter.com/","https://www.lennysnewsletter.com/feed"],"path":"/entities/lennys-newsletter","json":"/entities/lennys-newsletter.json","markdown":"/entities/lennys-newsletter.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d","revision":"cdea8f8f-f31a-4964-896e-41fe517174c1","revisionKind":"publication-id","title":"Lenny's Newsletter: Claire Vo’s first look at Meta’s Muse Wonder","url":"https://escapemeridian.com/readings/lenny-s-newsletter-claire-vo-s-first-look-at-meta-s-muse-wonder-61d83e4b"},"source":{"type":"source","id":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","revision":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","revisionKind":"sha256-source-text","title":"Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d","title":"Lenny's Newsletter: Claire Vo’s first look at Meta’s Muse Wonder","argument":"In Lenny's Newsletter, Claire Vo reports testing Meta’s Muse Wonder and Wonder Full on nearly 20 tasks in the How I AI bench, spanning prototyping, agentic workflows, coding, writing, and creative work. She says the results partly support Meta’s framing of Muse as a “personal and professional agent,” while identifying limits.\n\nVo scored the tasks with an LLM-as-a-judge pass and her own voice notes. Her overview says Muse ranked first on three agentic tasks, but the supplied page does not identify those tasks or give detailed scores. It also flags weak design output and compares Muse with other models on SVG illustration and short-form video.\n\nThe practical question in Vo’s account is where the model’s strengths translate into work she would actually use: the episode also examines email writing, voice-assistant tasks, and whether she will add Muse to her agent workflows. The available page lists those subjects but does not include the detailed results or her final workflow decision. Escape Meridian interpretation: this first-look account of one person’s bench does not establish performance across users or real-world tasks.","topicIds":["work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The supplied page contains an episode description and topic outline, not the detailed results, scores, or full discussion. The page does not identify the three agentic tasks where Muse ranked first or state Vo’s final decision about using it in her workflows.","speaker":{"name":"Claire Vo","roleAtSource":"Article author"},"source":{"title":"Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design","publisher":"Lenny's Newsletter","format":"Article","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","publishedAt":"2026-10-14T12:04:05+00:00","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"Claire Vo says she tested Meta’s Muse Wonder and Wonder Full on nearly 20 tasks across several kinds of work.","excerpt":"I put Meta’s new Muse Wonder (and Wonder Full) frontier models through the How I AI bench, which covers nearly 20 tasks across prototyping, agentic workflows, coding, writing, and creative work.","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Source-stated"},{"text":"Vo says she used an LLM-as-a-judge pass and her own voice notes to score the tasks.","excerpt":"I scored everything with an LLM-as-a-judge pass and my own voice notes","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Source-stated"},{"text":"The episode outline says Muse ranked first on three agentic tasks, but the supplied page does not name them.","excerpt":"The three agentic tasks where Muse ranked first, and why those categories matter","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Source-stated"},{"text":"The page presents Vo’s assessment as a first look, not a broad evaluation across users or real-world tasks.","excerpt":"then pulled together the first-look results you see here.","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","checkedAt":"2026-11-05T04:10:49.352Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=dChiPsd0uF4","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/2f168491-8e02-4135-9c6b-a9966afc9613_1456x1048.png","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"Which agentic tasks did Muse rank first on, and what did Vo conclude about using it in her own workflows?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Lenny's Newsletter: Claire Vo’s first look at Meta’s Muse Wonder","summary":"In Lenny's Newsletter, Claire Vo reports testing Meta’s Muse Wonder and Wonder Full on nearly 20 tasks in the How I AI bench, spanning prototyping, agentic workflows, coding, writing, and creative work. She says the results partly support Meta’s framing of Muse as a “personal and professional agent,” while identifying limits.\n\nVo scored the tasks with an LLM-as-a-judge pass and her own voice notes. Her overview says Muse ranked first on three agentic tasks, but the supplied page does not identify those tasks or give detailed scores. It also flags weak design output and compares Muse with other models on SVG illustration and short-form video.\n\nThe practical question in Vo’s account is where the model’s strengths translate into work she would actually use: the episode also examines email writing, voice-assistant tasks, and whether she will add Muse to her agent workflows. The available page lists those subjects but does not include the detailed results or her final workflow decision. Escape Meridian interpretation: this first-look account of one person’s bench does not establish performance across users or real-world tasks.","question":"Which agentic tasks did Muse rank first on, and what did Vo conclude about using it in her own workflows?","claims":[{"text":"Claire Vo says she tested Meta’s Muse Wonder and Wonder Full on nearly 20 tasks across several kinds of work.","excerpt":"I put Meta’s new Muse Wonder (and Wonder Full) frontier models through the How I AI bench, which covers nearly 20 tasks across prototyping, agentic workflows, coding, writing, and creative work.","support":"source-stated"},{"text":"Vo says she used an LLM-as-a-judge pass and her own voice notes to score the tasks.","excerpt":"I scored everything with an LLM-as-a-judge pass and my own voice notes","support":"source-stated"},{"text":"The episode outline says Muse ranked first on three agentic tasks, but the supplied page does not name them.","excerpt":"The three agentic tasks where Muse ranked first, and why those categories matter","support":"source-stated"},{"text":"The page presents Vo’s assessment as a first look, not a broad evaluation across users or real-world tasks.","excerpt":"then pulled together the first-look results you see here.","support":"interpretation"}],"limitations":["The supplied page contains an episode description and topic outline, not the detailed results, scores, or full discussion.","The page does not identify the three agentic tasks where Muse ranked first or state Vo’s final decision about using it in her workflows."],"mediaId":"388004979cb49712b4d7ec4b2d7f649f8fcf890b1928914b3205afbdc79838c0","correctionReason":null,"id":"61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d","publicationId":"cdea8f8f-f31a-4964-896e-41fe517174c1","version":1,"sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","sourceTitle":"Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design","publisher":"Lenny's Newsletter","publishedAt":"2026-10-14T12:04:05+00:00","originalPublished":{"value":"2026-10-14T12:04:05+00:00","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-04T12:36:44.834Z","createdAt":"2026-11-05T04:23:19.470Z","historical":true,"entityIds":["lennys-newsletter"],"topicIds":["work-and-agency"],"media":[{"id":"388004979cb49712b4d7ec4b2d7f649f8fcf890b1928914b3205afbdc79838c0","kind":"article","url":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-05T04:10:49.500Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."},{"id":"d2f660cd4d16b5af98d8913e4bfa6dd1cc5d3505a1b07ca0d13a3e26fdc5b7c4","kind":"video","url":"https://www.youtube.com/watch?v=dChiPsd0uF4","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","label":"Watch source","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-05T04:10:49.500Z","method":"publisher_association_and_head","contentType":"text/html","cacheUntil":1793851849500},"recommendationReason":"Observed on the acquired publisher source; availability checked."},{"id":"b6af37784a72cf56cc3a5c43f5c6686323e56e26ebc70a0c02c2382aab4b446e","kind":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/2f168491-8e02-4135-9c6b-a9966afc9613_1456x1048.png","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","label":"View source image","provenance":"publisher_page","verification":{"status":"verified","checkedAt":"2026-11-05T04:10:49.500Z","method":"publisher_association_and_head","contentType":"image/png","cacheUntil":1793852149500},"recommendationReason":"Observed on the acquired publisher source; availability checked."}],"sourceMedia":{"status":"found","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","checkedAt":"2026-11-05T04:10:49.352Z","items":[{"type":"video","url":"https://www.youtube.com/watch?v=dChiPsd0uF4","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-embed","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"},{"type":"image","url":"https://substack-post-media.s3.amazonaws.com/public/images/2f168491-8e02-4135-9c6b-a9966afc9613_1456x1048.png","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","attribution":"Lenny's Newsletter","basis":"publisher-metadata","availability":"verified","verifiedAt":"2026-11-05T04:10:49.500Z"}],"note":"Media declared by the original publisher; availability checked separately from the editorial reading."},"editorialDecision":{"outcome":"accept","reasonCodes":["useful_perspective"],"rubricVersion":"stream-admission-v5","mediaId":"388004979cb49712b4d7ec4b2d7f649f8fcf890b1928914b3205afbdc79838c0","confidence":0.8799999999999999,"provider":"typesafe","model":"jev-1.13.0","inputHash":"116eb45f45f814e23a2900aa35d306843548150edff142aaedae3b26ca96000c","decidedAt":"2026-11-05T04:10:50.784Z"},"provenance":{"textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observationId":"e2794b5c36a0e146795ade6b93cbf45f3e7fbe481f768c7451084a666de74f4c","retrievedAt":"2026-11-05T04:10:49.352Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"b3c8e596-cd25-425a-88fa-cd19df2873bd"},"reviewer":{"model":"gpt-6-luna","runId":"bc12903f-669e-41a7-85f8-89e5f4889d3e"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-05T04:23:19.470Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Claire Vo","url":"https://substack.com/@clairevo","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23484.author"},"assertionId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T04:10:49.352Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z"}},{"actor":{"name":"Claire Vo","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Claire Vo","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","locator":"head/meta[name=author|citation_author]"},"assertionId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T04:10:49.352Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z"}},{"actor":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/","kind":"unknown","actorId":null},"role":"publisher","scope":{"kind":"publication","locator":null},"literalCredit":"Lenny's Newsletter","status":"stated","provenance":{"basis":"article-publisher","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","locator":"document/html[1]/body[2]/div[1]/div[1]/div[1]/script[0]@23484.publisher"},"assertionId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-05T04:10:49.352Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z"}}],"participationCoverage":{"total":3,"returned":3,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":{"name":"Lenny's Newsletter","url":"https://www.lennysnewsletter.com/"},"sourceUrl":"https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good","snapshotId":"1f207d5930efafffd34c34936aedf89e322af16722a29e41c258b69603cca41d","contentSha256":"05b4d4f54f1d5adf296c8fe12ff888e709d02a3436e1ea04e01e88339e07ae39","textHash":"8bc5c4ee60e644e7553d40d85ec384904b1157c351fbc8594ff1d0664dfa4785","observedAt":"2026-11-05T04:10:49.352Z","basis":"publisher-page-metadata","sourceLinks":52,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/61d83e4bd965593070ef15a894ed3ff8f32418c694560a21c11ffaae9350147d/source"}}}],"audits":[{"publicationId":"cdea8f8f-f31a-4964-896e-41fe517174c1","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The draft correctly attributes the testing, scoring method and assessments to Claire Vo. It places the piece in Lenny's Newsletter, which matches the source URL and page, and keeps her judgments as her own claims.","excerpt":"I put Meta’s new Muse Wonder (and Wonder Full) frontier models through the How I AI bench"},{"dimension":"summary","status":"uncertain","explanation":"The draft says the results 'partly support' Meta's agent framing, but the outline says the framing 'mostly holds up,' which weakens Vo's verdict. It also mutes the headline thesis ('good for AI agents, bad for design') and her blunt 'it's not good' on design. Smallest repair: say 'mostly holds up' and reflect the agents-good, design-bad thesis. Central terms such as agentic, LLM-as-a-judge and SVG need term-library tooltips so general readers can follow.","excerpt":"Why Meta’s “personal and professional agent” framing mostly holds up, and where it doesn’t"},{"dimension":"date","status":"pass","explanation":"The displayed originalPublished date of 2026-10-14 matches the byline date on the page and the feed entry.","excerpt":"Claire Vo\nOct 14, 2026"},{"dimension":"support","status":"pass","explanation":"Each claim matches the source text. The draft accurately notes that the page does not name the three tasks or give Vo's final workflow decision. The first-look inference is explicitly labeled as Escape Meridian interpretation and carries a supporting excerpt. The question follows from real gaps in the page and does not presuppose an answer.","excerpt":"then pulled together the first-look results you see here."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct original article link, a supplied candidate. It is relevant and gives the easiest access to the source. The verified YouTube episode would also be a reasonable choice.","excerpt":null}],"createdAt":"2026-11-05T04:23:19.470Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}