Live data from Hacker News

Claude: Elevated errors across many models [resolved]

status.claude.com

111–120 of 173 posts

Re: Claude: Elevated errors across many models [resolved]

#111
post #21

I’ve been using Codex w GPT 5.5 more than Claude Code recently. I think Anthropic won the marketing game because Codex is quite good, even better IME.

One very annoying thing about Codex: You can't do anything until all MCP servers are loaded and connected (or failed).

Can you move it to background connection?

Re: Claude: Elevated errors across many models [resolved]

#112

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

> in windows terminal This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to…

I'm a professional C++ dev working in games, and windows is used everywhere , from games themselves to the network infrastructure(I've worked for 3 of the largest games publishers too).

Windows really has a fantastic support for C++ and rendering programmers imho, the tooling is world class and Visual Studio has no match as an IDE. Even if somehow my tools worked on Mac or Linux I'd still pick windows out of sheer convenience of using it for work.

But as things stand - all major console toolchains are windows only. If you're making a game for PlayStation, Xbox or Switch, you have to be on windows.

Re: Claude: Elevated errors across many models [resolved]

#113

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

> in windows terminal This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to…

About 60% to 70% of devs in IT use Windows. And it's closer to 95% in some countries, even first world ones.

Re: Claude: Elevated errors across many models [resolved]

#114

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

Or pi.dev - also super fast and simple. Claude Code is sluggish, buggy, slow. Typical big enterprise garbage. The only good thing at Anthropic are the models.

I ask Claude to implement non-regression tests. It works like magic. With a couple of modules checking for code quality, more magic. Add some online performance tests if relevant, and it is close to paradise. From time to time, send it to some blog pages and articles with implementation ideas and recommendations. Look for best practices and let it do the analysis and implementation job if it makes sense... T

Re: Claude: Elevated errors across many models [resolved]

#115

This is every few weeks, I cancelled Anthropic and now use Codex only. Anthropic has been a hot mess since at least december in my usage, and has only gotten worse in 2026.

I actually feel like it's gotten much better in the past 1-2 months? Admittedly a low bar.

Re: Claude: Elevated errors across many models [resolved]

#116
post #100

Earlier quoted context omitted.

FWIW Codex TUI is written (in large part) in Rust and is way less buggy, and a lot faster. When I was a regular Claude Code user I'd routinely get bizarre "scroll everything since the beginning of time in one massive flash on every update" bugs ... for months. Like, just there from the time I started using it in June '25 or so until I quit in March. I prefer it over opencode, which is my other option I use with my Co…

That particular bug seems to be gone. I'm using my own Ruby terminal, and it's more than fast enough for normal stuff, but it made that bug 10x more painful so I am particularly sensitive to it... Not seen it at all recently.

Good to hear. Over a slow ssh connection it made me want to tear my hear out

Re: Claude: Elevated errors across many models [resolved]

#117
post #53

Earlier quoted context omitted.

I have my qualms with Anthropic/Claude but they've also had to scale unfathomably fast and that is just hard to do regardless.

Yes but many of the challenges directly contradict the idea that "coding is a solved problem"

Not really.

Coding is probably solved, at least to a large extent, but that doesn't mean engineering is solved too.

This is like someone saying that the wright brothers solved sustained/powered human flight, and another person saying "well if that's the case, why do planes still crash? obviously flight isn't solved.". Well, there are always improvements, but planes can fly and llm's can code.

Re: Claude: Elevated errors across many models [resolved]

#118
post #71

I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy and work against their message. Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled. In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.

It's not just Windows where the rendering goes to shit immediate: any time I've got it open in tmux on Linux, it becomes a basket case in probably a few hours or less.

I've seen this too. I had a couple of instances inside a tmux session, and after some time, everything in there slowed down to a crawl. What I found interesting is that terminals outside tmux were fine.

Re: Claude: Elevated errors across many models [resolved]

#120

Earlier quoted context omitted.

Claude code + tmux is SO buggy. Things rendering all over the place.

Is this a new regression for others? I feel like I used it in a tmux setup without issues for 6+ months and only recently am I forced to Ctrl+L or resize the window constantly.

Yes, issues started happening for me about a week ago.
Post reply on HN