Jack Morris(@jxmnop):Question for LLM enthusiasts these days, one typically kicks off post training by distilling some reasoning trajectories from some other model. it's kind of like a sourdough starter so how was the *first* model post-trained? did humans write the original set of formatting traces from scratch? (this is why Inkling used a small number of Kimi traces btw)

Jack Morris

@jxmnop

research @engramlab // language models, information theory, science of AI

加入 October 2016

1.1K 正在關注 53.7K 粉絲

Jack Morris@jxmnop

2026.08.30 23:29

Question for LLM enthusiasts these days, one typically kicks off post training by distilling some reasoning trajectories from some other model. it's kind of like a sourdough starter so how was the *first* model post-trained? did humans write the original set of formatting traces from scratch? (this is why Inkling used a small number of Kimi traces btw)

341

轉發到社區

熱門用戶