composer-2

Tag

Cards List
#composer-2

@Potatoloogs: Cursor trains Composer 2: Pre-training lets the model "learn knowledge", RL lets the model know "who it is" a) Why Cursor trains its own models Think of a model like a hard drive—it can only store a limited amount of information. Cursor cares about only one thing: software engineering, and only inside Cursor...

X AI KOLs Timeline · 2026-06-05 Cached

Detailed walkthrough of Cursor's approach to training Composer 2: using Kimi 2.5 as the base, learning code knowledge through large-scale intermediate training, then large-scale RL to teach the model to write correct code in real environments, and using self-summarization to handle long contexts.

0 favorites 0 likes
#composer-2

@FeitengLi: Asynchronous, Sparse, and the Fifth Decimal Place: Engineering Details of Cursor Training Composer 2 https://lattifai.com/zh/podcasts/SequoiaCapital/UDTr9yUnLUI…

X AI KOLs Timeline · 2026-06-03 Cached

This article delves into the technical details such as asynchronous and sparse methods used in Cursor training Composer 2 model, and provides a comprehensive analysis of the RL infrastructure.

0 favorites 0 likes
#composer-2

@srush_nlp: Talk: Training Composer https://youtube.com/watch?v=uTgqYeVxy2c… Overview of the methods that we use at Cursor to build…

X AI KOLs Timeline · 2026-05-21 Cached

Cursor shared the training methods for its self-developed programming model Composer 2, including large-scale continuous pre-training, long-range reinforcement learning, and an internal benchmark CursorBench, which brings the model's programming performance to a top level.

0 favorites 0 likes
← Back to home

Submit Feedback