ECHO-2 is a new way to train AI with reinforcement learning that keeps a small, central trainer busy while sending the easy, cheap work (rollouts) to many low-cost computers spread around the world.
INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (about 12B active per token) trained with large-scale reinforcement learning and it beats many bigger models on math, coding, science, and reasoning tests.