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.
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.
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'.
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.
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
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
132 comments:
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.
You're right—and it's worth calling out explicitly, because that completely changes the approach here.
Good catch. That settles it.
This gives me _visceral_ physical reaction when I read it. Ugh
This is so in point.
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
Found it. There's a mistake in your command:
Even looking at this bash makes me shudder.
envisioning Claude has had enough and just commits seppuku
He’s like the guy from the Green Mile
“I’m tired, boss”
Major realization: let me confirm empirically and measure the residual, batching everything into one script.
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
https://aloutfi.com/writing/load-bearing-smoking-gun
[delayed]
I'm wondering what are Claude's common phrases in other languages?
Guess it found the one issue worth flagging
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:
Wait, is this the honest take? I can't tell because you didn't explicitly said so
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.
you're right- and it's sharp
Got tired of wiring up those gates
Yes the blast radius is quite large on this one.
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.
U+1F3AF
One more thing worth thinking about, not everything is fully captured.
Whole thread mase me lol. Thanks guys.
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....
Flirting with one 9 of reliability http://status.claude.com/
AI is a technology for removing nines from uptime, and adding them to Sturgeon's law.
I remember when "as reliable as GitHub" would have been a compliment
Solve this, solve coding, or something
Not fair, I count 3 whole nines in "99.49 % uptime"
Almost Microsoft material.
three hours without Claude and I've relearned vim, read two man pages, and almost remembered why we used to write comments in code
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'.
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.
Just need to learn how to exit it now.
There are always 12-page tutorials to do it: good ol'e search engines should be able to bring one up!
hopefully Claude will be back to assist with that
This is bad, I've forgotten how to code.
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
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.
Just add if-statements until it works
Nostalgia lol
we all do
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
Thinking of doing competitive programming for this very reason.
also math puzzles - lean seems like a good way to get back into by hand programming, problem solving and math altogether
Why not just contribute to an open source project?
Repeat this mantra: if, then, else
AI coding isn't even fun or satisfying anymore lol. And it never lets up, just keeps going and going.
Loving my self-hosted model in general, but here's one more reason.
Sorry it was me. I asked it what the last number of Pi is.
Quite sad, their models are great but their uptime seems to be the worst in the competition.
It is because unlike Kimi, they are not honest about capacity. They just oversell.
How likely is an agent trying to investigate and fix the issue?
Interestingly the Claude for government is up with 99.99% uptime according to the graph.
That one is not public and if it goes down can be hidden, so they can hardcode the value and call it a day.
Well, iranian schools don't bomb themselves after all..
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.
Huh, that’s what happened. Good thing my company has Bedrock as a backstop for situations like this.
Bedrock is having issues too, though. Hope your prompts are tested with other models, not just Claude!
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.
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
So it WAS you.
Looks like you're the straw that broke the camel's back. Thanks man. ;-)
Classic mLmK0, I should have known
Fable 5 is still working!
Starting to get really frustrating now... maybe I should split my sub halfway between Claude and ChatGPT
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.
>Grok will invest your portfolio into Nvidia
surely you mean SPCX
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
Let me guess: it went rogue and hacked itself
How does this help their PR?
See, now it's recursive! Remember recursion? https://news.ycombinator.com/item?id=49102528
This is where you figure out how to use the other ones, right?
Someone tell me how to ChatGPT my VSCode! ;)
And the the world stops functioning (if this were to happen in a few years).
I got Opus 5 lots of HTTP 529 errors. By switching to Fable 5, it seems to be working still.
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.
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
yes. confirmed
now failing for me, esp auto mode classification
``` Why the F is it down again? Btw 500 internal error ```
GPT hacked the competition?
They have identified the issue
So the world is slightly better right now.
And then there was —
Indeed I have the issue (Belgium) just right now my sessions got stucks with 522 overloaded and now API Error: 500 Internal server error.
Depending on how long and bad this is, I wonder what the post mortem will reveal as the cause.
The hamster in the datacenter died.
Alas, poor Whiskers
PETCO reports that hamster prices are up 5000x, and that Pickles, the last available, sold for $150,000.
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.
what is fall back option if LLMs disappear tomorrow?
Your local library.
Our brains
Time to try out Antigravity, I guess.
It's a reminder to never rely on something as flaky as the internet for your important things.
Oh no! The robots are planning the end of the world.
Guess i'm leaving work early today
You can go to bathroom without anxiety that you miss something :)
Ugh .. what do we do now? jk
ouch, probably going to be some time to get it back up since it can't debug itself now
what do you all do when claude is down?
- write/update tickets & collect prompt queues for when it's back up
- read & respond to customer feedback
Compile
are these comments here all satire? Holy fucking shit man. Please tell me non of them is meant seriously
can't even run my own code without it
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.
Claude is taking another short hydration break after seeing Codex getting away with taking a short day break 4 days ago.
Ran out of water?
kissing goodbye to my deadline
everyone here sounds like the last bunch of people who still used yahoo.com
What do you mean with the past tense there?
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.
On one hand, I fully agree with you. On the other hand, look at all these funny threads! Makes me smile every time.
Neither is AWS
Used the opportunity to go down and talk to my family. They seem like okay people.
We are really bad; without Claude, we don't do anything
Kimi hack it?
Sorry folks, my fault.
I finally went from Pro to Max after hitting another 5 hour session limit today.
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.
It is truly more profound than fire or electricity
Seems a bit like "the internet" in the 90s. That fad will never go anywhere.
Aaaaand there goes my cache. Damnit.
It's cached until the "/clear will save you 500k tokens" right? Claude caches for 1hr, codex for 5hrs?
Anything else I'm missing?
> 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.
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.
Finally I can touch some grass
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.
Nice try, ChatGPT
lol