I don't know about other people, but my experience with Anthropic's products outside of the models themselves has been atrocious. The models are really good obviously, and have changed how all of us work, but their client software, be it Claude desktop, Claude on the web and Claude Code is bug-ridden, with an incoherent feature set and invasive behaviors.
But why is the harness so bad when it’s built with the best models? And presumably models better than we have access to?
How can they claim coding is solved when Claude Code is so terrible?