2026-10-05 · America/Los_Angeles · 社区动态 · #4

Introducing Kardashev-0.7, the world’s first trained swarm made of 32 distinct models Trained with RL for Population…

Introducing Kardashev-0.7, the world’s first trained swarm made of 32 distinct models Trained with RL for Population Scaling (RLPS), 32 models organically develop specialization & complementary capabilities, delivering frontier performance at: - 0.007x ~ 0.02x of the inference https://t.co/XGDlZSW7tk

热度 57.4 / 100；排名与评分保留该期记录。