Re:Claude Opus 4.7 costs 20–30% more per session
by 9dev on Friday April 17, 2026 @02:05PM
(#47808779)
But that objective measure is exactly what we’re lacking in programming: There is often many ways to skin a cat, but the model only takes one. Without knowing about those it didn’t take, how do you judge the quality of a new model?
[ Parent
| on HN ]