Composer: Building a Fast Frontier Model With RL
AI Summary
Cursor's technical write-up of Composer — a mixture-of-experts model trained with RL across hundreds of thousands of concurrent sandboxed coding environments. Composer is positioned as the in-house engine specialized for software engineering, with frontier-quality output at ~4x the generation speed of comparable models. Documents the infrastructure (rewriting the VM scheduler to handle bursty training workloads) and the training-vs-production environment unification. Required reading on what it takes to ship a model tuned for the harness rather than the other way around.
31 more articles in this vault.
Import the full Agent Harnesses vault to Burn 451 and build your own knowledge base.
Content attributed to the original author (Cursor Team). Burn 451 curates publicly available writing as a reading index. For removal requests, contact @hawking520.