Claude Auto-Compact Mechanism Sparks Debate Over High Token Consumption
Users discovered that Claude's 'auto-compact' feature does not reduce context load as expected but instead defaults to loading the last 1 million tokens into the context. This mechanism causes rapid depletion of API usage limits (5-hour caps), sparking debates over billing logic and performance optimization.
Related Entities
Full Report
holy fuck. so auto compact basically loads last 1M tokens into context by default on claude?\n\nand here i thought they were summarising and reducing the context loads. \n\nno wonder people used to burn anywhere from 2%-15% 5h limits simply for auto compacting their sessions.","hashtag_entities":[],"smarttags":[]},"edit_control":{"__typename":"EditControlInitial","edit_tweet_ids":["2108393422658908495"]},"grok_translated_post_with_availability":{"is_available"},"id":"VHdlZXQ6MjEwODM5MzQyMjY1ODkwODQ5NQ==","legacy":{"entities":{},"lang":"en"},"media_entities2":[],"mention_entities":[],"quoted_tweet_results":{"id":"VHdlZXRSZXN1bHRzOjIxMDgyNzc4MzYyODUxNjE3OTg=