GitHub user zuozhiw added a comment to the discussion: Ambient "operator 
recommender" — predictive next-operator suggestions on the canvas

Hi @gupta-sahil01 thanks for looking into cursor, I think a custom-trained 
model is not very feasible for us, so for this one we should still stick to 
openly avaiable models. But cursor uses a smaller model for this task, so we 
should also consider using less powerful models, which are both cheaper and 
possibly faster. With this in mind I would suggest we proceed to next steps and 
do not stuck in researching for too long. Thanks. What would be a sensible next 
step?

GitHub link: 
https://github.com/apache/texera/discussions/5240#discussioncomment-17346881

----
This is an automatically sent email for [email protected].
To unsubscribe, please send an email to: [email protected]

Reply via email to