Yes.
Something appears broken.
5.7% complaint rate (3hr avg)
*
Claude Code v2.1.224
AI-generated summary
What share of all Claude mentions on X are complaints? Higher means more people are having problems. All times UTC.
Want to know when things go wrong?
No spam. Only spike alerts.
A sample of recent tweets about Claude AI, sorted by engagement. All dates UTC.Sample of recent Claude tweets (UTC).
i thought it was just me. Opus 5 is the first model that the more I use, the worse I like it. It goes off-track, does random things I didn't ask for, forgets other things, and constantly has those annoying guardrails, etc. Sorry, but GPT-5.6 is worlds better. I really don't und... show more
It's so petty that Claude still refuses to look for skills in ~/.agents/skills. Every time I hit this, I deduct 5 goodwill points from the Anthropic account.
Chat, I'm unironically a big fan of AI now I don't vibe code, or whatever, but it's ability to generate me slop Python scripts for reverse engineering, or it's ability to help me troubleshoot Linux gunk, is absolutely incredible. I'll say, "Hey ChatGPT, I've got this goop that ... show more
I believe the benchmarks that say the newest Claude models are really good at complex tasks. But for my own non-complex tasks, they’re worse because the clarity of its language seems worse and therefore harder to use.
Built by Prabal, Saransh, Sarthak
Have you ever wondered if Claude is actually getting worse, or if it's just you? ClaudeDown tracks public complaints about Claude AI across Twitter/X in real time, so you can see whether other people are experiencing the same issues.
Every hour, we collect complaint tweets, compare the volume against historical baselines for the same time of day, and flag when something looks off. The complaint-to-mention ratio helps separate genuine regressions from normal background noise.
This is a community project. The data is estimated, not exhaustive. But when hundreds of people independently start complaining about the same thing at the same time, that signal is hard to ignore.
Complaint volumes and baselines are estimates based on sampled Twitter data. Spikes are detected algorithmically and may include false positives.