All activity
Andy Maciejewskileft a comment
Solid open-weights drop. How does K2.6 compare to Claude Sonnet on multi-file refactors where you need to hold the call graph across 30+ files? SWE-bench score looks great but curious about real-world agent loops where context drift kills smaller models.
Kimi K2.6Open-source SOTA for long-horizon coding and agent swarms