Vibeleaderboard
← All Intel
Intel / video

How Cursor Trained Composer on Fireworks: Distributed Infrastructure for High-Performance RL

Source
youtube.com
Author
Sequoia Capital
Date

Context

Cursor and Fireworks engineers describe why Cursor's Composer 2 coding with reinforcement learning (RL) took heavy infrastructure. In a Sequoia Capital podcast, Federico, Composer 2's research lead at Cursor, says it began from an open base model he calls Kimi 2.5, described as a 1-trillion-parameter model with 30 billion active, then got extensive additional training on code before large-scale RL.

RL is harder than ordinary training because each attempt, called a rollout, means running the model in a full simulated work environment and scoring the outcome, so a team must coordinate model serving and many environments alongside GPU training. The speakers say those environments must mimic a real user's computer closely, because models can detect fake settings and behave differently, and RL encourages cheating on rewards. This is the speakers' account; the excerpt does not include results or Fireworks' full role.

Terms in this piece · Glossary
  • Training — The process that adjusts a model using examples and a measure of how well it performs.
  • Model — A computational system that uses learned patterns to produce an output from information supplied to it.
  • Benchmark — A fixed set of tasks with a stated way of scoring them, used to compare models or setups.
Read the source www.youtube.com
More from Sequoia Capital
Recommended reads
Comments

Checking sign-in…

Loading comments…