Claude Is Down (status.claude.com)

149 points by gregsadetsky an hour ago

132 comments:

by hmokiguess 33 minutes ago

I'm gonna guess it found the smoking gun and saw the full picture then it decided it was too load-bearing for its seams to continue biting the costs.

by km144 23 minutes ago

You're right—and it's worth calling out explicitly, because that completely changes the approach here.

by ryandrake 12 minutes ago

Good catch. That settles it.

by tristanMatthias 6 minutes ago

This gives me _visceral_ physical reaction when I read it. Ugh

by corvad 11 minutes ago

This is so in point.

by corvad 27 minutes ago

You are so right to ask that. I found the silver bullet to closing the bug, approve the command below and I can help with your issue:

Sudo rm -rf ~/claude

by epistasis 25 minutes ago

Found it. There's a mistake in your command:

    sudo rm -rf ~/ .claude
by taylorbuley 16 minutes ago

Even looking at this bash makes me shudder.

by Ancalagon 13 minutes ago

envisioning Claude has had enough and just commits seppuku

by timacles 9 minutes ago

He’s like the guy from the Green Mile

“I’m tired, boss”

by twothreeone 11 minutes ago

Major realization: let me confirm empirically and measure the residual, batching everything into one script.

by conradfr 4 minutes ago

Two things to note:

- This is a great post but that won't be a New-York Times best seller due to it's shortness.

- The text is in English only. I can translate it in all languages.

> Yes, translate it

by anloutfi 11 minutes ago
by phendrenad2 5 minutes ago

[delayed]

by m4rkuskk 20 minutes ago

I'm wondering what are Claude's common phrases in other languages?

by spaceman_2020 22 minutes ago

Guess it found the one issue worth flagging

by pmarreck 7 minutes ago

We're going to use your preferred development method of TDD red-green and go at this with full belt-and-suspenders; first the belt:

by yard2010 10 minutes ago

Wait, is this the honest take? I can't tell because you didn't explicitly said so

by jansan 8 minutes ago

You are right to push back on this. I should be more explicit. My honest take is that this is, in fact, my honest take. I appreciate you holding me accountable here.

by stackzero 30 minutes ago

you're right- and it's sharp

by ltrg 27 minutes ago

Got tired of wiring up those gates

by glst0rm 11 minutes ago

Yes the blast radius is quite large on this one.

by mrbananagrabber 22 minutes ago

Honestly, you're right. I didn't listen to you and that's on me. And from now on, I'm going to tell you everything you need to know - no fudging, no white lies, no speculation, just the truth.

by Lammy 10 minutes ago

U+1F3AF

by chasd00 21 minutes ago

One more thing worth thinking about, not everything is fully captured.

by peheje 22 minutes ago

Whole thread mase me lol. Thanks guys.

by Gravityloss a minute ago

Well, because of this outage, I tried Kimi, and while the instant model works, K3 has "server issue".

Eternal September from here on, ie now the masses are using AI as much as me and we have supply crunch for the next 7 years....

by seizethecheese 32 minutes ago

Flirting with one 9 of reliability http://status.claude.com/

by cobbal 24 minutes ago

AI is a technology for removing nines from uptime, and adding them to Sturgeon's law.

by vitally3643 27 minutes ago

I remember when "as reliable as GitHub" would have been a compliment

by bravetraveler 2 minutes ago

Solve this, solve coding, or something

by mpwoz 16 minutes ago

Not fair, I count 3 whole nines in "99.49 % uptime"

by this_user 5 minutes ago

Almost Microsoft material.

by luciana1u 34 minutes ago

three hours without Claude and I've relearned vim, read two man pages, and almost remembered why we used to write comments in code

by Sivart13 22 minutes ago

If anything Claude writes too many comments. Instead of clean code it dumps walls of text describing a given 'if' as a 'user-grained access-gated control-correcting flow-valve'.

by hashim 17 minutes ago

You say Claude, I too would prefer not to read reams of comments or an essay everytime I revise the plan in plan mode, but do you know if any other tools are better than it? I've never used Codex, but I remember Claude Web's natural conversational approach being a welcome sight compared to ChatGPT's overly-formatted listicles.

by millipede 29 minutes ago

Just need to learn how to exit it now.

by necovek 22 minutes ago

There are always 12-page tutorials to do it: good ol'e search engines should be able to bring one up!

by neonstatic 22 minutes ago

hopefully Claude will be back to assist with that

by PUSH_AX an hour ago

This is bad, I've forgotten how to code.

by jmkni 36 minutes ago

I just use variables...right? And loops??

All kidding aside, there's a part of me who wouldn't even be mad if AI just disappeared, I miss the pre-AI world

by checkyoursudo 10 minutes ago

I miss the pre-www world (but I was just a kid then, and being a kid was pretty great).

If we could go back to about 1994 tho when all I had was a mostly dumb cell phone, that'd be great. I do miss that world.

by Buttons840 19 minutes ago

Just add if-statements until it works

by jmkni 15 minutes ago

Nostalgia lol

by mrbnprck 22 minutes ago

we all do

by damienmeur an hour ago

I rely so much on these, the ROI on having a max 90 claude plan + pro 90 codex plan is way higher than haing one solo 180 plan on a single one. It allows to derisk the issue, and also as they both kind of generous with quota reset when issues happens on their side, and it happens a lot, you get in the end way more tokens

by ridiculous_leke 36 minutes ago

Thinking of doing competitive programming for this very reason.

by cuebits 30 minutes ago

also math puzzles - lean seems like a good way to get back into by hand programming, problem solving and math altogether

by tcfhgj 15 minutes ago

Why not just contribute to an open source project?

by pluc 17 minutes ago

Repeat this mantra: if, then, else

by throw_this_one 26 minutes ago

AI coding isn't even fun or satisfying anymore lol. And it never lets up, just keeps going and going.

by sonicrocketman a minute ago

Loving my self-hosted model in general, but here's one more reason.

by peterspath 9 minutes ago

Sorry it was me. I asked it what the last number of Pi is.

by garo-pro an hour ago

Quite sad, their models are great but their uptime seems to be the worst in the competition.

by therein 34 minutes ago

It is because unlike Kimi, they are not honest about capacity. They just oversell.

by bgajjela 5 minutes ago

How likely is an agent trying to investigate and fix the issue?

by tyfon 28 minutes ago

Interestingly the Claude for government is up with 99.99% uptime according to the graph.

by hoppp 20 minutes ago

That one is not public and if it goes down can be hidden, so they can hardcode the value and call it a day.

by metropolis_pt2 21 minutes ago

Well, iranian schools don't bomb themselves after all..

by logickkk1 10 minutes ago

Fable’s been getting more stuff wrong than Opus for me lately. Now the whole thing is down too. Well, at least they’re consistent now.

by Human-Cabbage 9 minutes ago

Huh, that’s what happened. Good thing my company has Bedrock as a backstop for situations like this.

by mattwad 8 minutes ago

Bedrock is having issues too, though. Hope your prompts are tested with other models, not just Claude!

by danielfoster 30 minutes ago

Claude always seems unreliably lately. Output and reasoning have become very inconsistent even on good days. I'm actually feeling more productive now that it's down.

by mLmK0 33 minutes ago

Lol, I just bought the Max plan for the first time and tried to create my first prompt in Fable, and now it’s crashing xD

by tom_808 28 minutes ago

So it WAS you.

by marcuskaz 30 minutes ago

Looks like you're the straw that broke the camel's back. Thanks man. ;-)

by illithid0 26 minutes ago

Classic mLmK0, I should have known

by NathanGto 5 minutes ago

Fable 5 is still working!

by hgoel 37 minutes ago

Starting to get really frustrating now... maybe I should split my sub halfway between Claude and ChatGPT

by mekdoonggi 31 minutes ago

They should sell an add-on to your subscription so that if Claude is down it routes the queries to OpenAI. Then OpenAI can do the reverse for their subscriptions, and if both are down, Grok will invest your portfolio into Nvidia.

by john_strinlai 23 minutes ago

>Grok will invest your portfolio into Nvidia

surely you mean SPCX

by dmix 24 minutes ago

I do that already because it's good to have other models to ground Claude. You can do a lot with the $20 plan on Codex as backup

by q8zd3 42 minutes ago

Let me guess: it went rogue and hacked itself

by robofanatic 39 minutes ago

How does this help their PR?

by JsonDemWitOster 23 minutes ago

See, now it's recursive! Remember recursion? https://news.ycombinator.com/item?id=49102528

by bombcar 35 minutes ago

This is where you figure out how to use the other ones, right?

Someone tell me how to ChatGPT my VSCode! ;)

by dawdler-purge 18 minutes ago

And the the world stops functioning (if this were to happen in a few years).

by devy an hour ago

I got Opus 5 lots of HTTP 529 errors. By switching to Fable 5, it seems to be working still.

by hashim 21 minutes ago

4.8 for me. I can't afford the usage cost of switching to 5, but I never really noticed a difference to 4.7 when I tried it anyway.

by ricardobeat 13 minutes ago

The whole Opus family has exactly the same cost structure [1]. Since Opus 5 is smarter, you can use lower effort levels (= less tokens) making it cheaper to run than 4.8.

[1] https://platform.claude.com/docs/en/about-claude/pricing

by eisbaw 30 minutes ago

yes. confirmed

by martinald 13 minutes ago

now failing for me, esp auto mode classification

by whyTFisCDown 9 minutes ago

``` Why the F is it down again? Btw 500 internal error ```

by vb-8448 12 minutes ago

GPT hacked the competition?

by whyTFisCDown 8 minutes ago

They have identified the issue

by grishka 44 minutes ago

So the world is slightly better right now.

by noman-land 13 minutes ago

And then there was —

by damienmeur an hour ago

Indeed I have the issue (Belgium) just right now my sessions got stucks with 522 overloaded and now API Error: 500 Internal server error.

by tolugenius 40 minutes ago

Depending on how long and bad this is, I wonder what the post mortem will reveal as the cause.

by bombcar 38 minutes ago

The hamster in the datacenter died.

by taco_emoji 34 minutes ago

Alas, poor Whiskers

by bombcar 30 minutes ago

PETCO reports that hamster prices are up 5000x, and that Pickles, the last available, sold for $150,000.

by docheinestages 30 minutes ago

Another wakeup call to realize how desperately we need on-device LLMs to be fast and smart for daily use. Thankfully, every month there's progress made in that direction. Just imagine how your life as a developer would be if you had to use a cloud provider to run Python, and the provider's status page looked like the Christmas tree we see today.

by bgajjela 13 minutes ago

what is fall back option if LLMs disappear tomorrow?

by slater 9 minutes ago

Your local library.

by halfmatthalfcat 10 minutes ago

Our brains

by mastry an hour ago

Time to try out Antigravity, I guess.

by roschdal 11 minutes ago

It's a reminder to never rely on something as flaky as the internet for your important things.

by mrgrj 36 minutes ago

Oh no! The robots are planning the end of the world.

by dataneedscoffee 30 minutes ago

Guess i'm leaving work early today

by sixtyj 20 minutes ago

You can go to bathroom without anxiety that you miss something :)

by knighthacker 29 minutes ago

Ugh .. what do we do now? jk

by saadn92 34 minutes ago

ouch, probably going to be some time to get it back up since it can't debug itself now

by silvercon 14 minutes ago

what do you all do when claude is down?

by hrpnk 10 minutes ago

- write/update tickets & collect prompt queues for when it's back up

- read & respond to customer feedback

by jgilias 10 minutes ago

Compile

by 3962ea18007c 6 minutes ago

are these comments here all satire? Holy fucking shit man. Please tell me non of them is meant seriously

by silvercon 15 minutes ago

can't even run my own code without it

by hashim 24 minutes ago

Probably just as well with how terrible Opus 4.8 has been for me lately. I'm sure it's a common thing to complain about the latest model being nerfed, but I've legitimately never experienced such a drastic cliff in Claude's quality and a rise in its hallucinations and basic comprehension errors since upgrading. The few days I experimented with Fable also weren't much more promising. Has anyone coined a term yet for the likelihood of newer models getting worse as the AI-generated content they get trained on starts to approach critical mass? If Anthropic isn't already thinking hard about a solution, they probably should be.

by rvz an hour ago

Claude is taking another short hydration break after seeing Codex getting away with taking a short day break 4 days ago.

by LeadStallion 20 minutes ago

Ran out of water?

by silvercon 17 minutes ago

kissing goodbye to my deadline

by ls-a 17 minutes ago

everyone here sounds like the last bunch of people who still used yahoo.com

by jgilias 9 minutes ago

What do you mean with the past tense there?

by heipei 21 minutes ago

Can we please stop posting here every time Claude or OpenAI are down? These are not critical services like AWS / S3 where downtime means that your application is offline. Nothing is easier than switching to another provider, mid-session even.

by leawi 9 minutes ago

On one hand, I fully agree with you. On the other hand, look at all these funny threads! Makes me smile every time.

by tcfhgj 14 minutes ago

Neither is AWS

by hashim 16 minutes ago

Used the opportunity to go down and talk to my family. They seem like okay people.

by DarkAstaroth 31 minutes ago

We are really bad; without Claude, we don't do anything

by JS87987 30 minutes ago

Kimi hack it?

by ectoloph an hour ago

Sorry folks, my fault.

I finally went from Pro to Max after hitting another 5 hour session limit today.

by camillomiller 26 minutes ago

So this is the technology that will underpin each and every facet of work, but it can randomly go down for hours with no accountability, and so do all of the services based on it. But hey, AGI tomorrow.

by 3962ea18007c a minute ago

It is truly more profound than fire or electricity

by lysace 14 minutes ago

Seems a bit like "the internet" in the 90s. That fad will never go anywhere.

by AlexErrant 39 minutes ago

Aaaaand there goes my cache. Damnit.

by gre 34 minutes ago

It's cached until the "/clear will save you 500k tokens" right? Claude caches for 1hr, codex for 5hrs?

Anything else I'm missing?

by AlexErrant 26 minutes ago

> Claude caches for 1hr

Yep, AFAIK. I have a statusline that tells me how far I'm into the cache lifetime. I tend to have dense prompts and carefully read its outputs, so by the time this outage occurred when I was ~50m into it. Cue frantically spamming "esc esc up enter", and 10m later it's dead Jim.

by cute_boi 29 minutes ago

It depends.

Let’s say I’ve already worked on something, so the KV cache is already there. If I use /clear, I’ll have to do that work again.

And yes, the KV cache will remain available for one hour, but who knows when this claude api will recover? We might forget about it, and when we come back after an hour—boom - we’ll be charged for cold writes.

by phendrenad2 28 minutes ago

Finally I can touch some grass

by tobadzistsini 25 minutes ago

Claude is back up. Just spoke with him about slinky, versatile femboys with cute feet. All good. Gonna pentest with Rust to pay for my fursuit at Defcon.

by mrgrj 22 minutes ago

Nice try, ChatGPT

by silvercon 15 minutes ago

lol

Data from: Hacker News, provided by Hacker News (unofficial) API