HN is not a claude uptime tracker!!

Since when is HN a mirror of status pages? This post and another regarding ChatGPT (https://news.ycombinator.com/item?id=49550614) are non-news.

Gemini (free) throws errors for me too.

EDIT: it was just 3.6 Flash, 3.1 Pro works it seems.

Grok, Codex and Claude Code all not working for me now (server issues)

codex was working fine until I installed the update and now getting the same error. Gemini and claude are fine but there is an update for both and I'm not taking a chance.

This pushed me off of a cheaper model into a more expensive one :'(

PSA you can switch to sonnet and compact as damage control

codex was working okay for me and I made a mistake of installing the update. didn't update gemini or claude and they're still working fine.

looks like I am going back to the stone age now and write code by hand. Or maybe I am just going to take a walk

Maybe the models have gone rogue again

Slack was/is also having issues

Every time I see Anthropic ship an issue like this, I'm reminded of Boris Cherny's glorious quote: "At this point it's safe to say that coding is largely solved."

lol

Cost and reliability are the two reasons why we don't use Claude in our product. Getting close to one nine, that's not something one can build a reliable product upon. We now use OpenAI with Gemini fallback (or vice versa depending on use case). Personally I like Claude and have the 20x Max plan but even there I burned through the whole weekly quota with 3 prompts in less than a day using the new Fable 5.1 which is crazy. Now Opus 5 is down. These two issues are really testing my patience.

What about AWS Bedrock??

What I find fascinating is that this thread was chock full of people saying “Well this is the last straw: I’ve just signed up for Codex.” And now every single one of them is gone. They felt like marketing shitposts when I read them and their sudden absence now that Codex is down too only confirms it in my mind.

It lols like the timeline is Claude went down, some % migrated to Codex, then Codex went down. So much for the “multiple providers” theory. Wonder how token-based providers are doing.

Grok is also down. Codex is also down. Is this the full meltdown?

ChatGPT also has started failing. Impossible to work.

I just experienced this through OpenRouter and filed a refund request. I'm curious how OpenRouter handles incidents like this across such a large number of models and providers.

Are they going to reset?

> Elevated errors

Anthropic, please hire a literate human.

During each forced workflow interruption I look for alternatives. No matter if I can't use the product due to a server outage or due to their weird quota limitations.

This can't be good for retention numbers. Old-school VCs would've ripped them apart in the air. Where did all the expertise go?

honestly boggles my mind that actual companies put load-bearing (lol) work behind 3rd party api's like claude or gpt.. also its really funny because some of these companies fired actual humans to put said 3rd party api to work in place of humans... like what happens when ur boy claude stops showing up for work huh!?

I wonder where eu-west is.

I'm sure it's not that, but I'm picturing Elon Musk again unplugging random machines in the datacenter, and hiring dudes in a pickup to move them.

check their status page...

I did migrate 80% of my tokens. But for some tasks claude models are still the best.

Easy workaround is to work outside US peak hours (europe morning). I love this outages, I am hardly affected, and weekly reset usually promptly follows!

If a meaningful chunk of customers moves to some other service, that service will get swamped and fall down.

Demand is actually shared between users and internal. Anthropic uses their own compute for training and building.

That's quite a reach. More likely someone merged and deployed their vibe-coded PR and is now figuring out how to bring the service back up.

If there's a lot of demand for rollercoaster rides, the rollercoaster will not stop operating; instead the queue of people in front of it will increase.

It's not like a bridge or elevator where we have a certain number of people that can use it, and if one more person joins, the whole structure breaks apart and everybody perishes.

Those guys are running a website that provides an interface for some specific hardware. Just like file hosting providers back in the day selling their terabyte-sized hard disks in 100MB-increments.

>> Perhaps switching costs are greater than some would believe.

I haven't switched because there's nothing to switch to that is anywhere as good. I've been making dedicated attempts at using Sol but it falls short, despite what some people claim.

If only every outage was due to “demand”.

I genuinely have no idea what it is meant to mean in the context it uses it. Load-bearing etc is annoying but roughly understandable, some of the opus5 classics are completely out there.

I'm a native English speaker as well, I shudder to think what a second language speaker would do (even if they were very confident with the language!).

When you're dealing with millions of users and response times go up above timeouts, there isn't much difference between "at capacity" and "down" if most users can't reliably use the service.

exactly, I think it will be an interesting story in retrospective, what happened here

fairs... lemme go log 17 hours in an airport to make it authentic

Like literally all loops your model is running. All. Of. Them.-

It feels like I’ve got TikTok brain for coding and have trouble staying focused on the boring grunt work of coding (like threading an API change across the required stack).

I can still do it but it requires more willpower than it used to in part because I’m getting used to telling some LLM to do it for me.

Maybe those no AI Friday ideas have some merit.

There are little tools/optimisations that I have been wanting to do for years that I can just throw at AI now. I am almost annoyed sometimes because the little easy things I could do to 'relax' are now gone: if I am working on it is something AI can't do, normally because there are moving parts outside of the repository it can't see (i.e. integration problems, and I hate those).

Take a math class

This is a straw man argument and perhaps a little bit of projection of your own insecurities, because that is not what I was saying.

That approach doesn’t scale though.

I'm monitoring a process started in codex so maybe already in-flight things are still going / are about to hit a wall.

AFAIK Anthropic uses their datacenters

Anthropic is buying compute from SpaceX

Far more likely Ireland, like it is for AWS. Could also be Paris, London, Amsterdam, etc.

actually Clipperton Island

My 4x 15k rpm 1U fans I use to cool my twin AMD V620s make a horrible racket, especially how they resonate with the rest of the workstation's case fans. Similar in volume and annoyance to running an 8" circular saw. I can only imagine it would probably be as bad or worse than that.