Back to feed
Cognition (Devin)Model Release4 hours ago2 min read

Cognition launches SWE-1.7 model with improved RL training techniques

HIGHLIGHTS
  • Cognition (Devin) launched SWE-1.7 model
  • Improved RL training techniques, infrastructure, training stability, high-quality data curation, and long-horizon task techniques
  • Achieves frontier-level intelligence at a lower cost, challenges the 'post-training ceiling' notion, and demonstrates the potential for RL to enhance model capabilities
Published:
Official Source (Official Blog)

Related Activities