Lucas Beyer (bl16)(@giffmana):So they say "three things we scaled". Let me translate: 1. "compute" - yep, that's compute. 2. "environments and harnesses" - actually, also compute. 3. "and grader compute" - you guessed it, that's also compute. joke aside, pretty cool to see their public live dashboard, including "cost so far" (!) (due to recent events/discussions: no, this QT is not sponsored. I don't do sponsor stuff, I'm here for the fun.)

2026.09.16 20:02

So they say "three things we scaled". Let me translate: 1. "compute" - yep, that's compute. 2. "environments and harnesses" - actually, also compute. 3. "and grader compute" - you guessed it, that's also compute. joke aside, pretty cool to see their public live dashboard, including "cost so far" (!) (due to recent events/discussions: no, this QT is not sponsored. I don't do sponsor stuff, I'm here for the fun.)

Fuli Luo@_LuoFuli

2026.09.16 18:52

Nearly half a year of silence. We spent it studying one problem: how far RL can scale. MiMo-V2.6 is in the middle of its RL run right now. Three things we scaled: compute (~2B tokens per step, 1568 prompts × 16 rollouts, fully async), environments and harnesses (multi-task agentic RL, mixed across multiple harnesses in one run), and grader compute (agentic in-group credit assignment, with test-case and rubric-based rewards). We'll open-source the details piece by piece over the coming weeks. Streaming the run:

490

轉發到社區

熱門用戶