Lucas Beyer (bl16)
@giffmana
Researcher (now: Meta. ex: OpenAI, DeepMind, Brain, RWTH Aachen), Gamer, Hacker, Belgian. Anon feedback:
✗DMs → email
가입 December 2013
648 팔로잉 중 152.8K 팬
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.)
더 보기
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:
더 보기
