{"version":"2.1.286","anchor":"auto-mode-classifier-classifierwording-experiment-removed","canonical_anchor":"auto-mode-classifier-classifierwording-experiment-removed","heading":"Auto mode's safety check stops testing two wordings","tier":"internal","area":"Auto Mode","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286\/e\/auto-mode-classifier-classifierwording-experiment-removed","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.286","markdown":"### Auto mode's safety check stops testing two wordings\n\nThe two-wording experiment in auto mode's safety check has ended, and the classifier now always uses a single wording\n\n**Unclear.** It is not stated which of the two wordings was kept.\n\n**What**\n\nIn auto mode, a safety check called a classifier decides whether each action may run without asking you. Until now, the classifier could be given one of two wordings, so the two could be compared. That choice has been removed, and the classifier now always uses one wording.\n\nThe wording in use is also no longer recorded in the usage data Claude Code reports about auto-mode decisions, or in the classifier's results.\n\n**Why**\n\nA comparison test between the two wordings is over. Everyone now gets the same classifier instructions.\n\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5"}