Links
Links for September 22, 2026
-
Really good migration discussion, including key decisions like incremental vs big bang migration
-
"Scaling RL, Fully Open-Sourced
Along the way we worked through the research and engineering problems of RL training, and we streamed the production run live as it happened. In under six days, MiMo-V2.6-Flash and MiMo-V2.6-Pro each completed 30 RL steps over roughly 750k trajectories, at a cost of about $0.85M and $2.62M respectively.”