Quite frankly, most seasoned developers should be able to write their own Claude Code. You know your own algorithm for how you deal with lines of code, so it's just a matter of converting your own logic. Becoming dependent on Claude Code is a mistake (edit: I might be too heavy handed with this statement). If your coding agent isn't doing what you want, you need to be able to redesign it.
All my information about this is being based on feels, because debugging isn't really feasible. Verbose mode is a mess, and there's no alternative.
It still does what I need so I'm okay with it, but I'm also on the $20 plan so it's not that big of a worry for me.
I did sense that the big wave of companies is hitting Anthropic's wallet. If you hadn't realized, a LOT of companies switched to Claude. No idea why, and this is coming from someone who loves Claude Code.
Anyway, getting some transparency on this would be nice.
I'm not sure this is a regression, at least how I use it - you can hit control + o to expand, and usually the commands it runs show the file path(s) it's using, and I'm really paranoid with it, and I didn't even notice this change.
This is why I am a big fan of self-hosting, owning your data and using your own Agent. pi is a really good example. You can have your own tooling and can switch any SOTA model in a single interface. Very nice!
This is exactly the right instinct. When you own the agent harness, you decide what's visible. I've been building my own tooling on top of Playwright for similar reasons — the feedback loop between 'what did the agent just do' and 'should I let it continue' is the core UX of any agent, not a detail to be abstracted away. Hiding it breaks the only trust mechanism the user has.
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.
As a heavy CC user, I appreciate a cleaner console output. If you really need to know which 3 files CC read, AI-assisted coding agents might not be for you.
Can we not like, just apply a patch? Or will anthropic be mad if I run their client with my own patch?
Nix makes it easy to package up esotheric patches reliably and reproducibly, claude lowers the cost of creating such patches, the only roadblocks Inforesee are legal.
"This is as bad as it's going to be" turning out to be wrong
They could change course, obviously. But how does the saying go again -- it's easier for a camel to go through the eye of a needle, than for a VC funded tech startup to not enshittify.
Often a codebase ends up with non-authoritative references for things (e.g. docs out of sync with implementation, prototype vs "real" version), and the proper solution is to fix and/or document that divergence. But let's face it, that doesn't always happen. When the AI reads from the wrong source it only makes things worse, and when you can't see what it's reading it's harder to even notice that it's going off track.
There are a lot of non developer claude code users these days. The hype about vibe coding lets everyone think they can now be an engineer. Problem is if anthropic caters to that crowd the devs that are using it to do somewhat serious engineering tasks and don't believe in the "run an army of parallel agents and pray" methodology are being alienated.
Maybe Claude Code web or desktop could be targeted to these new vibe coders instead? These folks often don't know how simple bash commands work so the terminal is the wrong UX anyway. Bash as a tool is just very powerful for any agentic experience.
I wanted a terminal feel (dense/sharp) + being able to comment directly on plans and outputs. It's MIT, no cloud, all local, etc.
It includes all the details for function runs and some other nice to haves, fully built on claude code.
Particularly we found planning + commenting up front reduces a lot of slop. Opus 4.6 class models are really good at executing an existing plan down to a T. So quality becomes a function of how much you invest in the plan.
>Try using it for a few days. We've been using this internally at Anthropic for about a month now, and found that it took people a few days to mentally switch over to the new UI. Once they did, it "clicked" and they appreciated the reduced noise and focus on the tools that actually do need their attention.
160 comments
[ 1.7 ms ] story [ 96.4 ms ] threadIt still does what I need so I'm okay with it, but I'm also on the $20 plan so it's not that big of a worry for me.
I did sense that the big wave of companies is hitting Anthropic's wallet. If you hadn't realized, a LOT of companies switched to Claude. No idea why, and this is coming from someone who loves Claude Code.
Anyway, getting some transparency on this would be nice.
What’s wrong with you, people? Are you stupid?
I mean I get it I guess but I'm not nearly so passionate as anyone saying things about this
What if you hit ctrl+o?
https://lucumr.pocoo.org/2026/1/31/pi/
> Compacting fails when the thread is very large
> We fixed it.
> No you did not
> Yes now it auto compacts all messages.
> Ok but we don't want compaction when the thread isn't large, plus, it still fails when the compacted thread is too large
> ...
Nix makes it easy to package up esotheric patches reliably and reproducibly, claude lowers the cost of creating such patches, the only roadblocks Inforesee are legal.
They could change course, obviously. But how does the saying go again -- it's easier for a camel to go through the eye of a needle, than for a VC funded tech startup to not enshittify.
Often a codebase ends up with non-authoritative references for things (e.g. docs out of sync with implementation, prototype vs "real" version), and the proper solution is to fix and/or document that divergence. But let's face it, that doesn't always happen. When the AI reads from the wrong source it only makes things worse, and when you can't see what it's reading it's harder to even notice that it's going off track.
Maybe Claude Code web or desktop could be targeted to these new vibe coders instead? These folks often don't know how simple bash commands work so the terminal is the wrong UX anyway. Bash as a tool is just very powerful for any agentic experience.
Programmers are just jealous that they are no longer the only ones that get to play pretend.
I don't know anything about you personally, but most "software engineers" are anything but.
I wanted a terminal feel (dense/sharp) + being able to comment directly on plans and outputs. It's MIT, no cloud, all local, etc.
It includes all the details for function runs and some other nice to haves, fully built on claude code.
Particularly we found planning + commenting up front reduces a lot of slop. Opus 4.6 class models are really good at executing an existing plan down to a T. So quality becomes a function of how much you invest in the plan.
Ah, the old "you're holding it wrong."