[blurbleblurble]

This might be pretty big. One of my biggest frustrations with smaller models (especially MoE) is their failure to track workflow state at a high level. I'm constantly reminding them what we decided on or asking them to revisit, and reminding them eats context.

Seems like this might make that a lot less painful. And if not off the bat, with some minimal tuning or even just good prompting.