“We actually put this out in a blog post. We basically used Jev to do essentially like massive trace analysis for online training.”

“A cheap, fast model that just classifies and gives feedback on rejections might be a really good way to bridge the gap between agents and infrastructure”

“‘We’re using other models for static analysis because it’s a waste of tokens…’”

“… very good RL controllers that are probably trained from motion imitation, and then fine-tuned with good RL that suits the robot's body… for the specific task of running really fast.”

“We're actually able to bias the model based off of the direct user feedback using some of these like online training methodologies. We're able to see like real upticks in user satisfaction, completion rates, decreased tool call failures”