You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm enjoying the recent release of cursor planning mode, but I've noticed that it can be very picky about which models you use (for both the generation, and the plan application phases).
The docs suggest using llama-3.3-70b-versatile, which I've found to work pretty well. I've also had success using gemini-pro for both stages (the non-pro gemini seems to struggle).
Curious what models folks are using in the community to get this working the best?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm enjoying the recent release of cursor planning mode, but I've noticed that it can be very picky about which models you use (for both the generation, and the plan application phases).
The docs suggest using
llama-3.3-70b-versatile
, which I've found to work pretty well. I've also had success using gemini-pro for both stages (the non-pro gemini seems to struggle).Curious what models folks are using in the community to get this working the best?
Beta Was this translation helpful? Give feedback.
All reactions