{"slug": "metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design", "title": "Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design", "summary": "Meta's new frontier models Muse Wonder and Muse Wonder Full ranked first on three agentic tasks in the How I AI bench, a roughly 20-task evaluation spanning prototyping, agentic workflows, coding, writing, and creative work, but produced poor design output, according to host Claire Vo's first-look results. Vo scored the models with an LLM-as-a-judge pass plus her own voice notes, and found Muse fast on one-shot work but slow on agent tasks, trailing Sonnet on voice assistant tasks and Opus 5.5, Astra, and Fable on SVG illustration and short-form video editing.", "body_md": "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. I scored everything with an LLM-as-a-judge pass and my own voice notes, then pulled together the first-look results you see here.\n\n**Listen or watch on [YouTube](https://youtu.be/dChiPsd0uF4), [Spotify](https://open.spotify.com/episode/26i50r5Xbbm5Tg1TeLXnqQ), or [Apple Podcasts](https://podcasts.apple.com/us/podcast/metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design/id1809663079?i=1000796296040)**\n\n### What you’ll learn:\n\n1. Why Meta’s “personal and professional agent” framing mostly holds up, and where it doesn’t\n2. What active focus mode actually does on long-running tasks, and whether it’s real\n3. The three agentic tasks where Muse ranked first, and why those categories matter\n4. What Muse’s design output actually looks like (it’s not good)\n5. How it compares to Sonnet on voice assistant tasks\n6. Where Muse lands on SVG and short-form video versus Opus 5.5, Astra, and Fable\n7. Whether I’m actually putting Muse into any of my agent workflows\n\n### Brought to you by:\n\n**[DX](https://getdx.com/howiai)**—Engineering intelligence for the AI era\n\n**[Jira AI SDLC](https://ad.doubleclick.net/ddm/trackclk/N320202.6053656HOWIAI/B36397005.454541156;dc_trk_aid=648366078;dc_trk_cid=262806969;dc_lat=;dc_rdid=;tag_for_child_directed_treatment=;tfua=;gdpr=$%7BGDPR%7D;gdpr_consent=$%7BGDPR_CONSENT_755%7D;ltd=;dc_tdv=1)**—Get your tokens’ worth with Jira\n\n### In this episode, we cover:\n\n([00:00](https://www.youtube.com/watch?v=dChiPsd0uF4)) Intro and what Muse Wonder is\n\n([01:19](https://www.youtube.com/watch?v=dChiPsd0uF4&t=79s)) Meta’s frontier capability claims\n\n([04:36](https://www.youtube.com/watch?v=dChiPsd0uF4&t=276s)) Muse code\n\n([06:06](https://www.youtube.com/watch?v=dChiPsd0uF4&t=366s)) Benchmark overview and how the How I AI bench works\n\n([07:51](https://www.youtube.com/watch?v=dChiPsd0uF4&t=471s)) Overall results and TL;DR verdict\n\n([11:53](https://www.youtube.com/watch?v=dChiPsd0uF4&t=713s)) Agentic tasks\n\n([13:36](https://www.youtube.com/watch?v=dChiPsd0uF4&t=816s&pp=0gcJCWMAwfN6Pr3D)) Email writing and voice assistant performance\n\n([14:35](https://www.youtube.com/watch?v=dChiPsd0uF4&t=875s)) Where Muse falls short\n\n([18:28](https://www.youtube.com/watch?v=dChiPsd0uF4&t=1108s)) SVG illustration results\n\n([19:33](https://www.youtube.com/watch?v=dChiPsd0uF4&t=1173s)) Short-form video editing\n\n([21:18](https://www.youtube.com/watch?v=dChiPsd0uF4&t=1278s)) Fast on one-shot work, slow on agent tasks\n\n([22:15](https://www.youtube.com/watch?v=dChiPsd0uF4&t=1335s)) Final verdict and where I’ll use Muse Wonder next\n\n### Tools referenced:\n\n• Meta Muse Wonder / Muse Wonder Full: [https://research.meta.ai/blog/muse-wonder](https://research.meta.ai/blog/muse-wonder)\n\n• Muse Code: [https://developer.meta.com/ai/lp/muse-code](https://developer.meta.com/ai/lp/muse-code)\n\n### Where to find Claire Vo:\n\nChatPRD: [https://www.chatprd.ai/](https://www.chatprd.ai/)\n\nWebsite: [https://clairevo.com/](https://clairevo.com/)\n\nLinkedIn: [https://www.linkedin.com/in/clairevo/](https://www.linkedin.com/in/clairevo/)\n\nProduction and marketing by [https://penname.co/](https://penname.co/). For inquiries about sponsoring the podcast, email [\\[email protected\\]](https://www.lennysnewsletter.com/cdn-cgi/l/email-protection).", "url": "https://wpnews.pro/news/metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design", "canonical_source": "https://www.lennysnewsletter.com/p/metas-new-muse-wonder-model-good", "published_at": "2026-10-14 12:04:05+00:00", "updated_at": "2026-10-14 23:46:53.289795+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-products"], "entities": ["Meta", "Muse Wonder", "Muse Wonder Full", "Claire Vo", "How I AI", "Muse Code", "Sonnet", "Opus 5.5"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design", "markdown": "https://wpnews.pro/news/metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design.md", "text": "https://wpnews.pro/news/metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design.txt", "jsonld": "https://wpnews.pro/news/metas-new-muse-wonder-model-good-for-ai-agents-bad-for-design.jsonld"}}