dots3-note Preview: Multimodal Agent for Long-Horizon Tasks

thetripathi58 · x · 2026-08-26

dots3-note preview is out, focusing on enabling AI to work continuously as tasks stretch across time, intent evolves, and the environment changes. It combines multimodal perception (images, speech, text) with tool use to execute actions via code and tools. Demonstrations include long-horizon tasks like software development, travel planning, wedding coordination, and e-commerce.

Related event: Rednote AI Lab Unveils dots3-note, a Multimodal Long-Horizon Agent Model(3 posts)→

Original post →

More from coding & agent

coding & agent channel →