I’ve been following Claude’s status updates for a while, and it’s actually refreshing to see this kind of transparency. Most companies just hide issues behind vague “technical difficulties” messages, but here you can clearly track uptime and incidents. It gives a lot more confidence when using the service daily, especially since many of us depend on it for real work. Downtime is frustrating, but knowing what’s happening makes a huge difference. I wish more AI and SaaS tools had a page like this—it feels more trustworthy and professional.
It looks like Claude Code switched the default model to Sonnet 4.5, even for max users who are paying for Opus. I had to set the environment variable ANTHROPIC_MODEL=opus to get opus back. Sonnet 4.5 indeed acts like a drunken monkey on the math-heavy legacy C++ codebase I'm working on.