01CPMD3174 former Claude Code customer here.

I’m wondering if it’s just me or does this response sound like it’s coming from someone who is out of touch with the reality of how people are using their product and instead of being empathetic, curious, and helpful is telling people in so many words it’s not our fault, you’re doing it wrong and “everyone” should be doing it the “right” way, which is how we do it.

I know it might come as a shock but not everyone who uses product has read the docs.

Also there is arguably nothing about using AI harnesses that’s “old hat” The technology came on the mainstream radar this year. Most people who use harnesses are still figuring out how to use them. And the rest of humanity probably doesn’t even know what the terms means.

Rather than telling everyone how they got it wrong, maybe next time you can elaborate on something like what “we are looking into what we can do to prevent this” means.

For the record, besides finding Claude overzealous and Anthropic’s usage limits relatively stingy (at least back in April when I dropped them), it was the arrogance of Anthropic’s staff and their public pontificating that led me to rolling with Codex, Gemini, and Qwen as my model stack.

You have to wonder how much of the AI backlash is driven by people not feeling how industry insiders communicate with them.

Anyways, we need good homegrown AI solutions. So, I’m hoping Anthropic follows through on helping prevent future incidents. And the other labs are paying attention so their leadership aren’t the next ones on HN playing defense when their products get called out.