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 so you can focus on what matters, diffs and bash/mcp outputs." He suggested that developers "try it out for a few days" and said that Anthropic's own developers "appreciated the reduced noise."
Cherny said that developers who wanted more detail could enable verbose mode. Responses were lackluster, with one person writing: "Verbose mode is not a viable alternative, there's way too much noise."
Another observation was that the new default output, such as "searched for 2 patterns, read 3 files," conveys no useful information. "It's not a nice simplification, it's an idiotic removal of valuable information," said a user.
Cherny responded to the feedback by making changes. "We have repurposed the existing verbose mode setting for this," he said, so that it "shows file paths for read/searches. Does not show full thinking, hook output, or subagent output (coming in tomorrow's release)."
The problem with this is that making verbose mode less verbose is a bad change for those who wanted the full details.
Cherny also participated in a lengthy discussion on Hacker News. "Claude has gotten more intelligent, it runs for longer periods of time, and it is able to more agentically use more tools... The amount of output this generates can quickly become overwhelming in a terminal, and is something we hear often from users," he said.
... continue reading