Claude Code is being dumbed down?

I've never heard of such a brutal and shocking injustice that I cared so little about! - Zapp

I mean I get it I guess but I'm not nearly so passionate as anyone saying things about this

> Read 3 fies (ctrl+o to expand)

What if you hit ctrl+o?

I just tested, it shows you which files it read, same as first example he gave "Where you used to see."

This comes up from time to time and although my experience is anecdotal, I see clear degradation of output when I run heavy loads (100s of batched/chunked requests, via an automated pipeline) and sometimes the difference in quality is absolutely laughable in how poor it is. This gets worse for me as I get closer to my (hourly, weekly) limits. I am Claude Max subscriber. There’s some shady stuff going on in the background, for sure, from my perspective and experience during my year or so of intense usage.

Yes and no. There are many not-trivial things you have to solve when using an LLM to help (or fully handle writing) code.

For example, applying diffs to files. Since the LLM uses tokenization for all its text input/output, sometimes the diffs it'll create to modify a file aren't quite right as it may slightly mess up the text which is before/after the change and/or might introduce a slight typo in text which is being removed, which may or may not cleanly apply in the edit. There's a variety of ways to deal with this but most of the agentic coding tools have this mostly solved now (I guess you could just copy their implementation?).

Also, sometimes the models will send you JSON or XML back from tool calls which isn't valid, so your tool will need to handle that.

These fun implementation details don't happen that often in a coding session, but they happen often enough that you'd probably get driven mad trying to use a tool which didn't handle them seamlessly if you're doing real work.