Ask HN: Why is Claude so bad at answering questions about Claude Code
A week or two ago I asked about 329 errors I was getting, and it pointed me to a non-existent status page. When it finally found the right status page, I asked it to read it and it refused
Just now, I asked if there was a Claude Code integration with GitHub. Claude gave me a generic "I don't have specific information" response and suggested checking official docs
In contrast, when I asked ChatGPT the exact same question, it did a quick web search across multiple sites and gave me a detailed answer with direct links to Anthropic's own docs about their official GitHub integration (and even a comment about considerations of automation given their recent new rate limits announcement)
This feels like a solvable problem. Couldn’t Anthropic just RAG their own docs to provide better answers about their own products? It's frustrating when their competitor gives better information about Anthropic's tools than Anthropic's own AI does
Seems like a basic product integration issue
Anyone else run into this?