Dispatches from the lab — product announcements, research notes, and field reports on what we're building and what we're learning.
A closed-loop control layer for model transformation
Actuator is a patent-pending closed-loop control layer for model transformation with live training-time monitoring and in-flight adjustment.
Read →Parallel Perspectives for Compositional Reasoning
We introduce Divergent-Convergent Attention (DCA), a transformer primitive that maintains parallel attention streams at different window sizes and reconciles them through learned periodic consensus.
Read →An autonomous research agent for ML science
We built Marvin because too much ML research time is still spent on preparation, context gathering, and logistics instead of the science itself.
Read →Adaptive Draft Length and Confidence-Based Early Exit
Elastic speculation delivers 30–50% lower latency and up to ~50% fewer speculative KV writes in our experiments, while preserving output quality.
Read →