Trying Claude Opus again after months of mostly using GPT-5.5, and I was pleasantly surprised. Opus feels better at picking up intent and understanding what I’m actually asking for.
Tried it today. It completed the (very well defined) task of migrating XCTests to Swift Testing and then it started a broader and unnecessary dependency refactor of the whole project, where I had to intervene and stop it. Feels very beta still.
Pull requests disappeared on GitHub for many (all?) users.
This is just the latest outage on a platform where reliability has been beyond unacceptable the last few months.
A fair question: at what point would customers move? How much pain is too much? And where do they move?