This is one of those “The future is already here — it’s just not evenly distributed” situations. Training is hard and expensive. Using is not. Whether you need to retrain for a given target is an architectural decision—it does make it harder to train (but sublinearly in targets).
This is one of those “The future is already here — it’s just not evenly distributed” situations. Training is hard and expensive. Using is not. Whether you need to retrain for a given target is an architectural decision—it does make it harder to train (but sublinearly in targets).