dots3-note Preview: first dots3 model to jointly understand text, vision and speech

SarahAnnabels · x · 2026-08-30

dots3-note Preview is the first model in the dots3 family to jointly understand text, vision, and speech. Combined with stronger coding, tool calling, and end-to-end result delivery, it closes the loop from perceiving a task to acting on it. A demo shows autonomous development of a Xiaohongshu VR experience.

Related event: rednote Open-Sources dots3-note: 280B-Parameter Multimodal Agent Model with 512K Context(5 posts)→

Original post →

More from coding & agent

coding & agent channel →