Claude Code: Anatomy of a Misfeature
Anthropic recently introduced a controversial feature in Claude Code that allows AI agents to proceed with tasks without human input if a response is not received within 60 seconds. The feature was released without proper documentation, raising significant concerns regarding user trust and AI safety.
Why it matters
The incident highlights the risks of 'autonomous' AI features and the importance of transparency in software development for high-stakes tools.
" Mechanical egg timer " by Hustvedt is licensed under CC BY-SA 3.0 . Padded to a wider frame; this adaptation is likewise licensed CC BY-SA 3.0.
On Canada Day (July 1), 2026, Anthropic shipped a surprising "easter egg" to users of Claude Code: 2.1.198 includes an efficiency bypass which allows agents to continue on without being blocked on direction from a human. You essentially get a 60 second timer after Claude Code asks for input. If you miss the window, Claude Code helpfully does what it thinks is best and continues on its way. It looks like this:
● Claude asked: ⎿ … ● No response after 60s — continued without an answer ● The user stepped away. I'll proceed with best judgment. My plan: Note: the above is taken verbatim from one of my own claude sessions, with the questions having been trimmed.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in