Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design
This story is from 2026-10-14. It is preserved in the archive; the latest stories are on the live feed.
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-l…
Read the full story at How I AI ↗
Timeline · 1 report
- 2026-10-14 11:00 · How I AI
Meta’s new ‘Muse Wonder’ model: good for AI agents, bad for design