As a zero-shot classifier, I expect that effectiveness is dependent on the data trained upon.Jev input … > Unstructured data (e.g. text) with an emphasis on structured program state.What pre-training data/model is Jev based on? Surely result effectiveness is dependent (outside of one’s own input as “state”) on that?
aryehof · · focus · HN ↗
Jev input … > Unstructured data (e.g. text) with an emphasis on structured program state.
What pre-training data/model is Jev based on? Surely result effectiveness is dependent (outside of one’s own input as “state”) on that?