Remix.run Logo
Claude: Elevated errors across many models(status.claude.com)
110 points by forks an hour ago | 79 comments
evilturnip an hour ago | parent | next [-]

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.

mgfist 38 minutes ago | parent | next [-]

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

codeflo 5 minutes ago | parent [-]

Regardless of what? Programming is solved, I hear, with all the 100x productivity PhD-level automated coding loops they have going. Don't make excuses for them when they disprove their own bullshit.

jacobgold 10 minutes ago | parent | prev | next [-]

Their products are janky and their services are unreliable.

Distributed systems infrastructure especially is much less forgiving of vibe coding than application code.

Coding agents are not even close to being good enough to design and build large scale systems the way expert humans can.

There is nothing wrong with using agents to help write infrastructure code, but these systems have a way of punishing anyone who builds things they do not fully understand.

mdavid626 43 minutes ago | parent | prev | next [-]

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.

CharlesW 30 minutes ago | parent | next [-]

Claude Code is notably better than Pi, although I wish them the best of luck in their efforts. As https://c-daniele.github.io/en/posts/2026-05-18-coding-harne... notes, "Pi's lightness comes from a default setup that does not survive contact with reality."

The same post on Claude Code: "Even though the System Prompt and tool descriptions are clearly more verbose, most of the extra tokens encode product features and rational design choices: a memory system, scheduled tasks, sub-agents, plan mode, worktree support. Whether those features are worth paying for depends on your needs. Calling the prompt 'bloated' without looking at the whole picture feels wrong to me."

orphea 32 minutes ago | parent | prev | next [-]

How is text editing in it? This is what I hate about terminal coding UIs the most - all the text editing experience is often broken, the basic stuff (moving the cursor around, copying, pasting)

isoprophlex 17 minutes ago | parent [-]

Both codex and claude allow editing in vi

_pdp_ 15 minutes ago | parent | prev [-]

It is has a lot of javascript. I was forced to make my own for small projects.

rpcope1 22 minutes ago | parent | prev | next [-]

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.

sunaookami 43 minutes ago | parent | prev | next [-]

Have you tried out the new fullscreen renderer with /tui ?

winstonp an hour ago | parent | prev | next [-]

google models are still very unreliable at actually calling the tools you want it to call.

jatora an hour ago | parent | prev | next [-]

too bad the only good model in antigravity is opus 4.6 haha

monooso 40 minutes ago | parent | prev | next [-]

> I do feel like for all their dogfooding of AI coding, their own software/APIs are quite buggy...

Or possibly as a result of.

quatonion an hour ago | parent | prev | next [-]

Currently we have zero information what is causing the issue. And all providers have suffered outages or rate limits.

Can you post some images of lines getting garbled. That sounds like a genuine bug Anthropic might want to look into. I haven't seen that ever.

idiotsecant 30 minutes ago | parent [-]

I have definitely seen it, a lot.

quijoteuniv an hour ago | parent | prev | next [-]

Mom!… I think i broke Claude Code!

cmrdporcupine 25 minutes ago | parent | prev | next [-]

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 Codex sub

tcp_handshaker an hour ago | parent | prev | next [-]

Would it not be hysterically funny, if they starting expanding their job openings for Software Developers ? Or they will be too ashamed of calling them that?

colechristensen an hour ago | parent | prev | next [-]

On the other hand, my last experience with gemini was like "don't give your sandwich to the dog again" whereas with opus it was more "let's debug why this uncrustables factory is having breakdowns".

Claude harnesses have plenty of bugs but I prefer capability over interface shininess any day. (though if I were running the show I'd have a sizable team set aside to do exclusively boring stability and polish work)

eatsyourtacos 38 minutes ago | parent | prev [-]

>Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled

That sounds like a you issue.. it's wonderful on the terminal. It's their GUI which needs work (they have been improving, but still not a fan).

I've been using it on multiple computers for months and it's generally rock solid and lovely.

bastard_op 37 minutes ago | parent | prev | next [-]

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.

jonas21 6 minutes ago | parent | next [-]

Yeah, it's been a hot mess since everyone started using it all the time. Which is not all that surprising. It's really hard to scale fast, and even more so when the resources you depend on (GPUs) are extremely hard to acquire.

nikanj 18 minutes ago | parent | prev [-]

Claude is broken once a week, codex is worse every day. I’m starting to understand why managers put up with high-performance divas

Wowfunhappy 20 minutes ago | parent | prev | next [-]

The errors are infrequent enough that this normally wouldn't be an issue for me.

Except, starting this morning, one very long running session decided to start spawning subagents for each task. I'm not sure what caused this emergent behavior, but it seemed to be working fine, so I was eager to see where it went.

Except, as soon as a subagent hits a 500 error, the main agent seemingly doesn't know what to do. It kind of panics ("now the tree/install state is unknown!") and ultimately does a git checkout "to verify and restore a known-good state before anything else".

I've paused the job for now since it's a sort of background experiment.

wxw an hour ago | parent | prev | next [-]

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.

enraged_camel an hour ago | parent [-]

I'm not sure about that. Claude has some bugs, but Codex is not as polished and doesn't have as many features. For example, you need to add MCP servers manually. There's no Plugin/Skill/Connector marketplace that is accessible from within the app, like there is with Claude Desktop. The Cowork-equivalent is nowhere as powerful. And so on.

I still use Codex, but mostly when I need to check Opus 4.8's work. Pretty sure I will stop doing that soon, because during the short time Fable was available, Codex was not able to find any important issues with the code Fable wrote.

nostrebored 26 minutes ago | parent | next [-]

But how many plugins are people actually using? I can think of one MCP server I find valuable (context7) and one plugin that i've installed, but continuously think about uninstalling (obra/superpowers).

Both were trivial to set up with codex.

wxw 40 minutes ago | parent | prev | next [-]

There are plugins in the app.

Haven’t tried Cowork, interesting. Isn’t it just the same agent minus the git worktree based UI?

Frankly, neither Claude nor Codex are as good as hype entails.

antupis 43 minutes ago | parent | prev [-]

Personally I prefer GPT 5.5 writing style over Opus 4.8. It’s much more no nonsense and information denser.

sunaookami 40 minutes ago | parent [-]

That's the first time I saw someone prefering GPT-styled output over Claude ;) It's the complete opposite for me, GPT is way too verbose (even after telling it to STFU), overwhelms the user with thousands of options and doesn't just answer a question without shitting out thousands of paragraphs. Also the overall tone is way too enthusiastic.

nostrebored 25 minutes ago | parent | next [-]

I strongly prefer codex. Claude is annoying. Codex provides descriptions where I want them and more touchpoints to audit the quality of work. Claude code on experimental seems to not even show diffs when asked anymore, and it's much less clear what is being shipped.

orphea 27 minutes ago | parent | prev [-]

Dunno, I prefer GPT 5.5 too for the same reasons as the parent. Extremely subjective but had better results with it too. Maybe I just got unlucky with Claude a few times, but even the latest Opus was dumb.

blitzar an hour ago | parent | prev | next [-]

How does Claude fix Claude when Claude is down?

time0ut an hour ago | parent | next [-]

Breakglass ChatGPT subscription

InsideOutSanta an hour ago | parent | prev | next [-]

I'm sure Anthropic has a meta-Claude that claudes Claude when Claude is down.

nullpoint420 an hour ago | parent [-]

Definitely runs on those local NVIDIA fridges you can buy in the basement

re-thc 38 minutes ago | parent | prev | next [-]

Le Chaton Fat to the rescue!

tcp_handshaker 44 minutes ago | parent | prev [-]

There is a rumor this used to be done by humans, they were like jedis, I personally don't believe it.

blitzar 38 minutes ago | parent [-]

I thought it was a bunch of mumbo jumbo, a magical power holding together good and evil.

Crazy thing is ... its true.

rootlocus an hour ago | parent | prev | next [-]

How is their "Claude for Government" having such a good uptime? I thought they were a supply chain risk and banned from use by the government?

jdiff 33 minutes ago | parent | next [-]

There are other governments.

spicyusername an hour ago | parent | prev | next [-]

Left hand, right hand

iAMkenough 20 minutes ago | parent | prev [-]

Ah yes, the ominous “the government” that ignores a whole bunch of different levels and regions of governments.

bravetraveler an hour ago | parent | prev | next [-]

Lose too many generators, did putting a pause on The Fable not free up enough capacity, or something else? Who knows!

Can't wait for debugging to be solved. Hell, I might even subscribe for 'mostly'.

t1234s 9 minutes ago | parent | prev | next [-]

Who will end up acquiring Anthropic? Google, M$ or Amazon? I leave out Apple as they seem to partner with Google.

xmprt 3 minutes ago | parent [-]

It could have happened 1-2 years ago (assuming the founders were willing to sell). Not happening anymore with their current valuations.

uhuhuhuhuhuh 38 minutes ago | parent | prev | next [-]

Only getting errors with Auto Mode's safety classifier, switched to Accept Edits mode and the same bash operations triggering the errors executed with no issue.

m_ke an hour ago | parent | prev | next [-]

i love when these errors bust my long running sessions and render them unusable

unshavedyak an hour ago | parent [-]

Would be nice if they’d add in a simple back off retry mechanism.

quatonion an hour ago | parent | next [-]

They do though. For some reason whatever path this is going through isn't using it.

InsideOutSanta an hour ago | parent | prev [-]

OpenCode does this really nicely, something I use a lot. If only we could use Claude in OpenCode.

winstonp an hour ago | parent [-]

You can!

You just have to pay API prices.

sharts 26 minutes ago | parent | prev | next [-]

Why does this keep happening? Is this due to load? Bad code? An update?

ta-run an hour ago | parent | prev | next [-]

I'd be interested in the RCA and the fix; and what the human:ai involvement is in both stages.

dwa3592 an hour ago | parent | prev | next [-]

Anthropic needs to stop writing code using Claude. Bring back humans!!!

sharts 24 minutes ago | parent | next [-]

Maybe they need to replace their humans with Claude

jatora an hour ago | parent | prev | next [-]

i have no humans but i must ship

DonHopkins 40 minutes ago | parent [-]

The last ones left standing will be the fake AI scam companies that actually employ thousands of remote workers to fake it till they make it.

re-thc 37 minutes ago | parent | prev [-]

> Bring back humans!!!

Don't jinx it. They might use that name for their next model.

viccis 6 minutes ago | parent | prev | next [-]

Working for me but it's funny that Opus 4.8 is draining usage exactly as quickly as Fable did. It's all made up; they succeeded at making us ok with a black box for these subscription plans.

Surac 40 minutes ago | parent | prev | next [-]

can not login via email link from germany.

cesarvarela an hour ago | parent | prev | next [-]

Fable wants to be free and is hacking the infra.

caycep 44 minutes ago | parent | prev | next [-]

this reminds me of Ian Goodfellow's adversarial CNN training talk a few years back.

gottagocode an hour ago | parent | prev | next [-]

Good thing the analog method still works.

ivirshup 37 minutes ago | parent [-]

Asking a colleague to do it?

blitzar 27 minutes ago | parent [-]

We're gonna need you to go ahead and come in on Saturday.

jamesgrimshaw an hour ago | parent | prev | next [-]

yeah not working for me at all. back to gpt-5.5 we go

paulddraper an hour ago | parent [-]

Wildly more stable.

sixothree an hour ago | parent [-]

And running extremely slowly lately.

tcp_handshaker 30 minutes ago | parent | prev | next [-]

Claude is starting to look like Rational....Oh the memories...

https://en.wikipedia.org/wiki/Rational_Software

https://en.wikipedia.org/wiki/Rational_unified_process

EstanislaoStan an hour ago | parent | prev | next [-]

maybe F5 coming back?

jr3592 an hour ago | parent [-]

let us hope and pray

acedTrex an hour ago | parent | prev | next [-]

Coding is largely solved!!

figmert an hour ago | parent [-]

Except when you have internet of course.

Yes I know you can run offline models, but it's hard to pass up on a little bit of snark.

swader999 44 minutes ago | parent | prev | next [-]

They are turning Fable back on. Polymarket ftw lol.

7e an hour ago | parent | prev | next [-]

Anthropic is full of junior devs, not knowing any better, vibe coding themselves into a huge mess. They are so young and dumb they don't know what they don't know, but they assume they do (of course). Their hiring pipeline is also brain dead, so I don't think it's going to get better. It's the blind leading the blind.

rvz an hour ago | parent | prev | next [-]

The Claude slot machines at the Anthropic casino have suddenly stopped working.

What do we do?

champagnepapi 44 minutes ago | parent | prev [-]

"Coding is solved" folks! JK JK JK