Yacine calls Isaac Sim horribly inefficient; reply: just use MJX
cixliv · x · 2026-08-31
Yacine MTB (ex-OpenAI) calls NVIDIA's Isaac Sim "the most horribly inefficient crap trainer out there". The top-flavored reply is simply "mjx bro" — pointing to MJX (MuJoCo XLA), Google's JAX/XLA GPU-accelerated physics simulation that powers many low-cost robot RL pipelines. A short exchange capturing the Isaac Sim vs MJX sentiment split in the embodied-AI training community.
Related event: Dev Slams NVIDIA Isaac Sim as Inefficient, Community Suggests MJX(2 posts)→
More from Embodied
- Using an iPhone 13 mini as a Reinforcement Learning Environment — willcb · 2026-09-01
- Avatar with Whole-Body Touch, Spatial Hearing, and Physical Voice in One Simulation — bhartsb · 2026-09-01
- NVIDIA Introduces ADEPT: Zero-Shot Real-World Transfer of Sim-Trained Visuo-Tactile Policies — dr_alphalyrae · 2026-09-01
- Unitree G1 performs aerial flips in forest powered by BeyondMimic — CyberRobooo · 2026-09-01
- SpaceX Removes 12.1 Tons of Debris from Boca Chica Beach — DimaZeniuk · 2026-09-01
- Chinese Humanoid Robots Dominate IFA: UBTECH, Unitree, and More — CyberRobooo · 2026-09-01