This is what they get for not reading our antislop paper (ICLR 2026) and using our anti-slopped sampler/models, or Kimi (which is remarkable relatively non sloppy)

https://arxiv.org/abs/2510.15061

I thought normies would have caught onto the EM dash, overuse of semicolons, overuse of fancy quotes, lack of exclamation marks, "It's not X, it's Y", etc. Clearly I was wrong.

Is Kimi still non-sloppy? When I switched to 2.5, it suddenly felt noticeably less creative and base-model-like, more sycophantic, and it hasn't gone aggro at all. Feels like a lot of the magic is gone.