News for hackers. Stuff that matters.

A comment on Cursor Composer: Building a fast frontier model with RL. Parent comment

Re:Cursor Composer: Building a fast frontier model with RL by srush on Wednesday October 29, 2025 @01:48PM (#45750484)
The blog talks about the training process. Specifically we trained with RL post-training on coding examples.
[ Parent | on HN ]
Re:Cursor Composer: Building a fast frontier model with RL by chis on Wednesday October 29, 2025 @01:58PM (#45750637)
Makes sense, but what model was used for the base? Is it some open-source model, and you're not at liberty to disclose?
[ Parent | on HN ]
Re:Cursor Composer: Building a fast frontier model with RL by W0WL0LXD on Friday October 31, 2025 @02:46PM (#45775316)
not a Cursor employee but still a researcher, it’s Zhipu/Z.ai GLM-4.6/4.5. there’s traces of Chinese in the reasoning output + its the only model that would make sense to do this with RL, and is a model that already delivers near SOTA performance + is open-source/open-weight.

Cursor Composer and Windsurf SWE 1.5 are both finetuned versions of GLM.

[ Parent | on HN ]
Re:Cursor Composer: Building a fast frontier model with RL by chaidhat on Saturday November 01, 2025 @03:37AM (#45779877)
interesting, thank you
[ Parent | on HN ]
Re:Cursor Composer: Building a fast frontier model with RL by chaidhat on Wednesday October 29, 2025 @02:48PM (#45751293)
that's cool thanks!
[ Parent | on HN ]