Comment Comment by michaelbuckbee I ran a quick eval to see what this looks like qualitatively vs just calling Opus 4.7 or GPT 5.5 directly.As expected, Fusion was 7x slower and 4x the cost.This isn't a knock against it, just that it I think this places Fusion into a "use it only when you need it" category.https://3fpi5avcqq.evvl.io/ parent michaelbuckbee 4 months ago
As expected, Fusion was 7x slower and 4x the cost.
This isn't a knock against it, just that it I think this places Fusion into a "use it only when you need it" category.
https://3fpi5avcqq.evvl.io/