Hacker News new | ask | show | jobs
by NewsaHackO 35 days ago
How are Anthropic's production applications poor quality? Other than memory use (which unfortunately is the industry standard nowadays) Claude Code is pretty solid.
4 comments

Claude code is by far the buggiest piece of software I interact with, If the underlying model weren’t so good, I would never opt to use it.

It takes multiple seconds to launch, random lines disappear in the scroll back, it’s internal state gets messed up causing the TUI to show duplicate and/or offset lines, and it frequently causes some kind of GPU buffer corruption causing the entire terminal env to show garbage.

>It takes multiple seconds to launch,

Yes, this is the ubiquitous memory issue that I mentioned. Unfortunately, it is now the baseline in all modern apps.

>random lines disappear in the scroll back, it’s internal state gets messed up causing the TUI to show duplicate and/or offset lines,

I haven't seen this issue, other than when I am using a shell that is bugged and does it with all TUI/console programs (usually a virtualized shell which I resized). Do you have a reproducible example of this?

Baseline for “modern” apps, what? We’re talking about a terminal application here, there is definitely, most-assuredly ways to write something that does exactly what Claude Code does with a teeny fraction of the resource requirements.

The trick is not bringing React into the terminal.

(FWIW, I have a link to a TUI harness in my profile that uses 50MB of ram and about 1% CPU while streaming, even in giant contexts)

+1. Claude Code shows that _even while the model is incredible_, you still need proper engineering discipline to ship stable (and good) software.
Their "safety" system that arbitrarily flags things.

Tons of examples of innocuous strings setting it off and sometimes with financial impact like the OpenClaw/hermes thing (just having the word "hermes" would insta deplete your quota and start charging you API rates in extra usage)

The hermes trigger was a bug and they fixed it in a few hours. But bad news carries far and wide.
I read the Github issue. They also initially refused a refund until the whole thing blew up

Here's another one https://github.com/anthropics/claude-code/issues/52809

It's definitely not an isolated incident

Literally on the HN homepage today: https://news.ycombinator.com/item?id=48645386
Their product features are a venn diagram, so depending on the tool you use, you may or may not have access to a "Claude" feature

i.e.

- design is only available in web

- cowork is only available in desktop, sharing projects only works in chat, not cowork, which is arguably the more valuable place to have that feature (re: multiplayer like tag). SSO only works if you type your email, the "login with google" button be damned, and only after you finish typing your email does the login button text change.

- cli has a number of features only available there, with the cowork equivalent having a different name iirc

If you admin/support other people using the breadth of tools, you will see more of the slop they sling

Dispatch... Remote Control... it's baffling