Anthropic tries to hide Claude's AI actions. Devs hate it
Briefly

Anthropic tries to hide Claude's AI actions. Devs hate it
"Read 3 files (ctrl+o to expand),"
"Claude Code is being dumbed down."
"When I'm working on a complex codebase, knowing what context Claude is pulling helps me catch mistakes early and steer the conversation,"
"this isn't a vibe coding feature, it's a way to simplify the UI so you can focus on what matters, diffs and bash/mcp outputs."
Anthropic updated Claude Code to hide file names in progress output, collapsing detailed file actions into summary lines like 'Read 3 files (ctrl+o to expand)'. Developers object because visible filenames are needed for security checks, immediate context validation, auditing conversation history, and avoiding wasted tokens when interrupting wrong actions. Anthropic's lead for Claude Code defended the change as a UI simplification and suggested using verbose mode for full details; internal developers reportedly appreciated reduced noise. Many developers find verbose mode impractical due to excessive noise and say the new default provides no useful information, creating usability and financial concerns.
Read at Theregister
Unable to calculate read time
[
|
]