Anthropic Limits Claude Code in Response to User Complaints

Anthropic has recently faced complaints from its users regarding the use of Claude Code, their AI tool. Users reported that they were reaching their usage limits much faster than expected. Lydia Hallie, a representative from Anthropic, explained that the main reasons for this issue are the stricter limits applied during peak hours and sessions using contexts of 1 million tokens, which are becoming increasingly large.

In response to these concerns, Anthropic has made several improvements. The company has fixed some bugs, although none of them resulted in incorrect billing. Additionally, efficiency enhancements have been implemented, and pop-ups have been added to the product to better inform users.

To optimize the use of Claude Code, Lydia Hallie recommends using Sonnet 4.6 instead of Opus, as the latter consumes the limits about twice as quickly. She also suggests disabling the Extended Thinking feature when it is not needed, starting new sessions rather than continuing old ones, and limiting the context window. Users who still experience abnormally high usage are encouraged to report it via the feedback function.