Anthropic tries to hide Claude's AI actions. Devs hate it
Summary
Anthropic's Claude Code update conceals file access details, prompting backlash from developers who rely on this information for effective coding and oversight.
Why It Matters
The change in Claude Code's output affects developers' ability to monitor AI actions, potentially leading to errors and inefficiencies. Understanding AI behavior is crucial for maintaining control and optimizing performance in coding tasks.
Key Takeaways
- Developers need visibility into AI file access to prevent errors.
- The update simplifies output but may hinder effective oversight.
- User feedback indicates a strong preference for detailed information.
- The debate highlights the importance of transparency in AI tools.
- Changes to output settings can impact productivity and trust in AI.
Devops 35 Anthropic tries to hide Claude's AI actions. Devs hate it 35 The software doesn't show what files it's working on Tim Anderson Mon 16 Feb 2026 // 10:14 UTC Anthropic has updated Claude Code, its AI coding tool, changing the progress output to hide the names of files the tool was reading, writing, or editing. However, developers have pushed back, stating that they need to see which files are accessed. Version 2.1.20 collapsed the output so that instead of showing, for example, the file names and how many lines were read, it would just print "Read 3 files (ctrl+o to expand)," according to a post complaining that "Claude Code is being dumbed down." The full details can still be accessed with the keyboard shortcut, but constantly invoking this is annoying and impractical. Developers have many reasons for wanting to see the file names, such as for security, for knowing immediately if Claude is pulling context from the wrong files, and for easy audit of past activity by scrolling through conversation. "When I'm working on a complex codebase, knowing what context Claude is pulling helps me catch mistakes early and steer the conversation," one person wrote. There's also a financial impact. If developers spot that Claude is going down a wrong track, they can interrupt and avoid wasting tokens. A GitHub issue on the subject drew a response from Boris Cherny, creator and head of Claude Code at Anthropic, that "this isn't a vibe coding feature, it's a way to simplify the UI...
