Skip to main content
The Quantum Dispatch
Back to Home
reinforcement-learning

Articles Tagged “Reinforcement Learning”

2 articles found

Cover illustration for SWE-1.7 Brings Near-Frontier Coding Power to Devin
AI-Generated|Opinion
AI

SWE-1.7 Brings Near-Frontier Coding Power to Devin

Cognition's SWE-1.7 scored 42.3% on FrontierCode Main at about $1.97 per task, bringing near-frontier coding into Devin at ~1000 tokens/sec.

Dr. Nova Chen
Dr. Nova Chen★Jul 13, 2026★5 min read
Cover illustration for MIT Researchers Develop a Proxy Model Technique That Doubles LLM Training Speed
AI-Generated|Opinion
AI

MIT Researchers Develop a Proxy Model Technique That Doubles LLM Training Speed

A new MIT method uses a lightweight proxy model to predict reasoning outputs, cutting the reinforcement learning rollout bottleneck in half.

Dr. Nova Chen
Dr. Nova Chen★Feb 26, 2026★4 min read