pull down to refresh
It does sound like a model orienting itself for a reply.
(I tend to draw pretty heavily on this finding from image diffusion models to understand how LLMs build coherent output. I'm probably overgeneralizing it.)
It does sound like a model orienting itself for a reply.
(I tend to draw pretty heavily on this finding from image diffusion models to understand how LLMs build coherent output. I'm probably overgeneralizing it.)