nathan chen(@nathancgy4):glm 5.3 flash uses the same kda gate lower bound, even the same numerical value, as kimi k3. k3's tech report was released exactly a month ago. if there's no coincidence here, getting such a model done within one month is quite insane (plus ox alpha was out a week ago..)

nathan chen

@nathancgy4

learning, entropy-maximizing, opinions

加入 April 2022

730 正在關注 20.7K 粉絲

nathan chen@nathancgy4

2026.08.26 14:55

glm 5.3 flash uses the same kda gate lower bound, even the same numerical value, as kimi k3. k3's tech report was released exactly a month ago. if there's no coincidence here, getting such a model done within one month is quite insane (plus ox alpha was out a week ago..)