Elevated errors across many models

(status.claude.com)

314 points | by pablo24602 1 day ago

42 comments

  • dinkleberg 1 day ago
    Props to them for actually updating their status page as issues are happening rather than hours later. I was working with claude code and hit an API error, checked the status page and sure enough there was an outage.

    This should be a given for any service that others rely on, but sadly this is seldom the case.

    • palcu 22 hours ago
      Thank you! Opening an incident as soon as user impact begins is one of those instincts you develop after handling major incidents for years as an SRE at Google, and now at Anthropic.

      I was also fortunate to be using Claude at that exact moment (for personal reasons), which meant I could immediately see the severity of the outage.

      • koakuma-chan 22 hours ago
        It's important for companies to use their own products.
        • awesome_dude 21 hours ago
          Unless using your own dogfood prevents you from fixing it if it breaks

          https://www.theguardian.com/technology/2021/oct/05/facebook-...

          I have a memory that Slack fell into this trap too (I could be wrong)

          • hiddencost 19 hours ago
            Facebook notoriously had to cut open the doors to one of their data centers.

            Google SRE still keeps IRC available in case of an emergency.

          • antonvs 19 hours ago
            Now I’m imagining the folks at Slack gritting their teeth and using MS Teams
      • aduwah 22 hours ago
        Take my condolences, Sunday outages are rough
      • nrhrjrjrjtntbt 20 hours ago
        Sweet. Hopefully it is more than instinct but a codified at Anthropic. I.e. a graduate engineer with little experience can assess and raise incident if needed.
    • LanceH 23 hours ago
      Confusingly, I was trying to debug something with a 529, and this outage really had me going for a minute.
      • cevn 21 hours ago
        The 529 is coming from inside the house?!
    • arach 23 hours ago
      Same as you and I was glad to see the status page - hit subscribe on updates

      Claude user base believes in Sunday PM work sessions

      • gwd 22 hours ago
        As a solo bootstrapped founder, I take my sabbath sundown on Saturday to sundown on Sunday. Sunday evening therefore is generally the start of my work week.
      • airstrike 22 hours ago
        Sunday PM builder, reporting in.
      • taytus 20 hours ago
        Sunday? What is that?
      • exe34 23 hours ago
        hah I ran out of tokens a bit before it hit I reckon.
        • rnewme 23 hours ago
          same here, and I just got started, Hm..
    • smcleod 20 hours ago
      Indeed! I checked their status page within 2 minutes of having issues and it was updated to show they had detected it.
    • Buttons840 21 hours ago
      "There's a problem and we already know about it" is so much better than "there's a problem and we don't know about it and/or are hoping it will magically go away and that we won't be embarrassed".
      • dpkirchner 20 hours ago
        "If we admit to it we may have to compensate per SLAs, so dishonesty it is!"
    • fragmede 23 hours ago
      Seldom? Most status pages I've seen do eventually get updated, just not within that first critical 3 minutes.
  • palcu 23 hours ago
    Hello, I'm one of the engineers who worked on the incident. We have mitigated the incident as of 14:43 PT / 22:43 UTC. Sorry for the trouble.
    • l1n 22 hours ago
      Also an engineer on this incident. This was a network routing misconfiguration - an overlapping route advertisement caused traffic to some of our inference backends to be blackholed. Detection took longer than we’d like (about 75 minutes from impact to identification), and some of our normal mitigation paths didn’t work as expected during the incident.

      The bad route has been removed and service is restored. We’re doing a full review internally with a focus on synthetic monitoring and better visibility into high-impact infrastructure changes to catch these faster in the future.

      • ammut 20 hours ago
        If you have a good network CI/CD pipeline and can trace the time of deployment to when the errors began, it should be easy to reduce your total TTD/TTR. Even when I was parsing logs years ago and matching them up against AAA authorization commands issued, it was always a question of "when did this start happening?" and then "who made a change around that time period?"
      • giancarlostoro 21 hours ago
        I don't know if you guys do write ups, but cloudflare's write ups on outages is in my eyes the gold standard the entire industry should follow.
        • Arcuru 20 hours ago
          When I was at Big Corp, I loved reading the internal postmortems. They were usually very interesting and I learned a lot. It's one of the things I miss about leaving.

          A tech company that publishes the postmortems when possible always get a +1 in my eyes, I think it's a sign of good company culture. Cloudflare's are great and I would love to see more from others in the industry.

        • boondongle 20 hours ago
          A big reason for that is it comes from the CEO. Other providers have a team and then at least 2 to 3 layers of management above them and a dotted line legal counsel. So the goal posts randomly shift from "more information" to "no information" over time based on the relationships of that entire chain, the customer heat of the moment, and personality.

          Underneath a public statement they all have extremely detailed post-mortems. But how much goes public is 100% random from the customer's perspective. There's no Monday Morning QB'ing the CEO, but there absolutely is "Day-Shift SRE Leader Phil"

        • bflesch 20 hours ago
          Cloudflare deploys stuff on Fridays, and it directly affected shopify, one of their major ecommerce customers. Until they fix their internal processes all writeups should be seen as purely marketing material.
          • giancarlostoro 8 hours ago
            I absolutely see it as marketing, and it is effective because I still appreciate the write ups. Arguably any publicly traded company should be letting their investors know more details about outages.
      • 999900000999 22 hours ago
        Was this a typo situation or a bad process thing ?

        Back when I did website QA Automation I'd manually check the website at the end of my day. Nothing extensive, just looking at the homepage for piece of mind.

        Once a senior engineer decided to bypass all of our QA, deploy and took down prod. Fun times.

        • spike021 20 hours ago
          Depending on how long someone's been in the industry it's more a question of if, not when, an outage will occur due to someone deciding to push code haphazardly.

          At my first job one of my more senior team members would throw caution to the wind and deploy at 3pm or later on Fridays because he believed in shipping ASAP.

          There were a couple times that those changes caused weekend incidents.

          • MobiusHorizons 18 hours ago
            I think you meant to write “when, not if” instead of “if, not when”
            • spike021 16 hours ago
              heh, probably. that's what I get for writing a comment while walking my dog.
        • userbinator 19 hours ago
          In these times, it could be "the AI did it".
        • weird-eye-issue 22 hours ago
          [flagged]
      • wouldbecouldbe 22 hours ago
        Trying to understand what this means.

        Did the bad route cause an overload? Was there a code error on that route that wasn’t spotted? Was it a code issue or an instance that broke?

        • bc569a80a344f9c 21 hours ago
          It says network routing issue.

          Network routes consist of a network (a range of IPs) and a next hop to send traffic for that range to.

          These can overlap. Sometimes that’s desirable, sometimes it is not. When routers have two routes that are exactly the same they often load balance (in some fairly dumb, stateless fashion) between possible next hops, when one of the routes is more specific, it wins.

          Routes get injected by routers saying “I am responsible for this range” and setting themselves as the next hop, others routers that connect to them receive this advertisement and propagate it to their own router peers further downstream.

          An example would be advertising 192.168.0.0/23, which is the range of 192.168.0.0-192.168.1.255.

          Let’s say that’s your inference backend in some rows in a data center.

          Then, through some misconfiguration, some other router starts announcing 192.168.1.0/24 (192.168.1.0-192.168.1.255). This is more specific, that traffic gets sent there, and half of the original inference pod is now unreachable.

          • disqard 21 hours ago
            Thank you for that explanation!
        • mattdeboard 21 hours ago
          it means their servers were unreachable due to network misconfig.
      • colechristensen 20 hours ago
        The details and promptness of reporting are much appreciated and build trust, so thanks!
      • tayo42 21 hours ago
        I was kind surprised to see details like that in a comment, but clicked on your personal website and see your a Co-founder, so I guess no one is going to repremand you lol
    • giancarlostoro 21 hours ago
      Any chance you guys could do write ups on these incidents similar to how CloudFlare does? For all the heat some people give them, I trust CloudFlare more with my websites than a lot of other companies because of their dedication to transparency.
      • l1n 21 hours ago
        We're considering this!
        • giancarlostoro 20 hours ago
          I already love the product, and I think it would be great to see. Even if its not as "quickly" as CloudFlares (they post ASAP its insane) I would still be happy to see postmortem threads. We all learn industry wide from them.
    • nickpeterson 23 hours ago
      The one time you desperately need to ask Claude and it isn’t working…
    • dan_wood 23 hours ago
      Can you divulge more on the issue?

      Only curious as a developer and dev op. It's all quite interesting where and how things go wrong especially with large deployments like Anthropic.

    • dgellow 22 hours ago
      Hope you have a good rest of your weekend
    • Chance-Device 23 hours ago
      Thank you for your service.
    • g-mork 22 hours ago
      it's still down get back to work
  • irishcoffee 1 day ago
    I’m imagining a steampunk dystopia in 50 years: “all world production stopped, LLM hosting went down. The market is in free-fall. Sam, are you there?”

    Man that cracks me up.

    • lxgr 23 hours ago
      Everybody using the same three centralized inference providers? That would be as absurd and unrealistic as everybody hosting in us-east-1 and behind Cloudflare today!
    • adonovan 22 hours ago
      “A lone coder, trained in the direct manipulation of symbols—an elegant weapon from a more civilized age—-is now all that stands between humanity and darkness.” etc
    • michelsedgh 1 day ago
      Just like the internet, or Cloudflare going down?
      • irishcoffee 1 day ago
        No, not even close
        • patcon 23 hours ago
          Agreed. When cloudflare (ugh, aka the internet) goes down, we can't access information to think and work through. ("the fuel" in some metaphor)

          But what about when LLMs go down and a good chunk of a whole generation won't even know how to think, when the remote system goes down? (Is the ability to think "the engine" of self and agency in this metaphor?)

          We are building a wildly irresponsible context to exist in.

        • bdangubic 23 hours ago
          it is much worse, I forgot how to push to remote so deploys are delayed :)
    • jsight 23 hours ago
      I remember hearing Karpathy refer to these outages as a worldwide "intelligence brownout".

      Crazy: https://www.youtube.com/shorts/SV4DMqAJ8RQ

    • cdelsolar 22 hours ago
      Claude code cut me off a few days ago and I _seriously_ had no idea what to do. I’ve been coding for 33 years and I suddenly felt like anything I did manually would be an order of magnitude slower than it had to be.
      • cantalopes 20 hours ago
        You can always use gemini cli, its pretty good
        • prmph 20 hours ago
          Nah, I've now resolved to never use it, it'd a total time waster. When it works it's decent, but it does not work like half of time for me.
      • bdangubic 21 hours ago
        you can’t say things like this on HN these days :)
    • teaearlgraycold 23 hours ago
      The nice thing is unlike Cloudflare or AWS you can actually host good LLMs locally. I see a future where a non-trivial percentage of devs have an expensive workstation that runs all of the AI locally.
      • breatheoften 23 hours ago
        I'm more and more convinced of the importance of this.

        There is a very interesting thing happening right now where the "llm over promisers" are incentivized to over promise for all the normal reasons -- but ALSO to create the perception that the "next/soon" breakthrough is only going to be applicable when run on huge cloud infra such that running locally is never going to be all that useful ... I tend to think that will prove wildly wrong and that we will very soon arrive at a world where state of art LLM workloads should be expected to be massively more efficiently runnable than they currently are -- to the point of not even being the bottleneck of the workflows that use these components. Additionally these workloads will be viable to run locally on common current_year consumer level hardware ...

        "llm is about to be general intelligence and sufficient llm can never run locally" is a highly highly temporary state that should soon be falsifiable imo. I don't think the llm part of the "ai computation" will be the perf bottleneck for long.

      • PunchyHamster 20 hours ago
        I'd imagine at some point the companies will just... stop publishing any open models precisely to stop that and keep people paying the subscription.
        • teaearlgraycold 10 hours ago
          All we need is one research group somewhere in the world releasing good open models.
      • lxgr 23 hours ago
        I’m fairly sure you can also still run computers locally and connect them to the Internet.
        • irishcoffee 23 hours ago
          Ah, you need to buy into this dystopia wholesale. The internet is also down because the LLMs fucked up the BGP routing table, which congress agreed (at the time) should run through the LLM interface.

          Imagination, either the first or last thing to die in 2075.

          • lxgr 23 hours ago
            Congress administrating BGP? Now we’re talking dystopia!
            • irishcoffee 22 hours ago
              “Hey folks, did you know in 100 years you can’t just call the town doc? Nah, you need to go get a referral. No, for real. Yeah, yeah, that is in fact a compound fracture. I can’t treat it without a referral. Congress made the rules.”

              Is it so different?

      • colordrops 23 hours ago
        What's the best you can do hosting an LLM locally for under $X dollars. Let's say $5000. Is there a reference guide online for this? Is there a straight answer or does it depend? I've looked at Nvidia spark and high end professional GPUs but they all seem to have serious drawbacks.
        • teaearlgraycold 10 hours ago
          I’m cheating your budget a bit, but for $5600 you can get an M3 Ultra with 256GB of RAM.
        • cft 23 hours ago
          • colordrops 21 hours ago
            That's nice, thank you, I've joined and will follow. They don't seem to have a wiki or about page that synthesizes the current state of the art though.
      • exe34 23 hours ago
        I think it's possible, but the current trend is that by the time you can run x level at home, they have 10-100x in the frontier models, so if you can run today's Claude.ai at home, then software engineering as a career is already over.
        • teaearlgraycold 10 hours ago
          You can run quite powerful models at home on a maxed out Mac Studio. The difference between those and SoTA is more like 2x.
        • pstuart 23 hours ago
          My poorly informed hope is that that we can have mixture of experts with highly tuned models on areas of focus. If I'm coding in language Foo, I only care about a model that understands Foo and its ecosystem. I imagine that should be self-hostable now.
          • tsimionescu 15 hours ago
            A model that only understands, say, Java is useless : you need a model that understands English and some kind of reasoning and has some idea of how the human world works, and also knows Java. The vast majority of the computational effort is spent on the first two, the second is almost an afterthought. So, a model that can only program in Java is not going to be meaningfully smaller than a model that can program in ~all programming languages.
          • exe34 15 hours ago
            my suspicion is that this is not how intelligence works. creativity comes from cross breeding ideas from many domains.
            • pstuart 2 hours ago
              Sure, but in the context I was considering, creativity itself wasn't a concern.

              For coding, creativity is not necessarily a good thing. There are well established patterns, algorithms, and applications could reasonably be construed as "good enough" to assist with the coding itself. Adding a human language model over that to understand the user's intents could be considered an overlay on the coding model.

              I confess that this is willful projection of my hope to be able to self-host agents on affordable hardware. A frontier model on powerful hardware would always be preferable but sometimes "good enough" is just that.

      • cft 23 hours ago
        That's the only future of open source that I can see.
      • szundi 23 hours ago
        Those good ones are not even close though - or are they
    • PunchyHamster 20 hours ago
      "We vibe coded the problem into existence but now the LLM is down we can't vibe fix it"
    • sergiotapia 22 hours ago
      Like if electricity went out, no? Same deal.
      • irishcoffee 22 hours ago
        Imagination.

        “So sorry, we can’t read the WiFi signal from your generator. We don’t know how much to tax you for the emissions. Sadly, we can’t allow it to start.”

        The story writes itself.

  • Stratoscope 15 hours ago
    I was chatting with Claude this morning about a trip to Chicago where I visited the wonderful Field Museum among other places. An excerpt:

    Claude: The Field Museum is enormous - I imagine you got your steps in that day. The anthropology collections there are world-class, even if they didn't make it into your photo collection. Sometimes the experience is more important than the documentation. Did you have a favorite exhibit beyond the dinosaurs?

    Me: Oddly enough, the anthropology and human history section! Now I need to take another visit to Chicago to get pictures of those.

    [No response from Claude]

    [40 minutes pass while I have breakfast]

    Me: Looks like I caught you during your morning nap. Every two and a half year old should get a good nap now and then!

    Claude: Ha! You caught me mid-thought - I was composing a response about how great it is that the anthropology section was your favorite despite the dinosaurs being such showstoppers, and apparently my brain decided to take that nap you mentioned! ... Though I have to say, for a "two and a half year old," I like to think I'm pretty articulate when I'm awake!

  • tgtweak 7 hours ago
    There really should be an http header dedicated to "outage status" with a link to the service outage details page... clients (for example, in this case, your code IDE) could intercept this and notify users.

    503 is cool and yes, there is the "well if it's down how are they going to put that up" but in reality most downtimes you see are on the backend and not on the reverse proxies/gateways/cdns where it would be pretty trivial to add a issues/status header with a link to the service status page and a note.

    • embedding-shape 7 hours ago
      Something something if everyone used HATEOS this wouldn't have been a problem something something
  • sebastiennight 23 hours ago
    In the Claude.ai chat, this was announced to me as

        "You have reached the messages quota for your account. It will reset in 2 hours, or you can upgrade now"
    
    Either I have perfect timing for reaching my quota limits, or some product monetization manager deserves a raise.
    • manquer 23 hours ago
      More likely that error handling is not well implemented - i.e Either backend is not throwing the equivalent of 429/402 errors or the gateway is not handling the errors well and returns this message even though a 429 is being thrown.
      • manuisin 21 hours ago
        This sort of thing keeps me skeptical of AI quite a bit. ChatGPT also has non sensical errors messages for random failures, Gemini too. These companies have infinite compute and yet they haven't been able to implement reliable/graceful error handling in 2+ years for a chat app? Why are they promising us they can replace all developers?
    • frankdenbow 22 hours ago
      i ran into the same thing, i thought it was just timing
  • michelsedgh 1 day ago
    If they shut down opus 4.5 I'll cry
    • agumonkey 23 hours ago
      i already heard people ask for more api credits embarassed like drug addics
      • XCSme 23 hours ago
        Just a few more credits and it will finally fix that bug without introducing new ones, exactly how I asked
        • baobabKoodaa 23 hours ago
          I can stop any time I want, and in fact I am going to stop. Just one more (bug)fix.
          • michelsedgh 23 hours ago
            This joke is getting old kinda Opus4.5 handles all the bugs in one go and also doesn’t introduce new ones at least for me. Very rarely i get stuck with it like i did with past generations of AI
            • agumonkey 23 hours ago
              How long the usual self debugging cycle ? it seems to be around 10 minutes for me (untyped language)
    • teaearlgraycold 23 hours ago
      I think we’re all very happy with the pricing on it.
      • tcdent 23 hours ago
        I use it as much as my brain can handle and I never exceed my Max plan quota.
        • AnotherGoodName 23 hours ago
          Just a warning for those not on the max plan; if you pay by the token or have the lower tier plans you can easily blow through $100s or cap your plan in under an hour. The rates for paying by the token are insane and the scaling from pro to max is also pretty crazy.

          They made pro have many times more value than paying per token and then they made max again have 25x more tokens than pro on the $200 plan.

          It’s a bit like being offered rice at $1 per grain (pay per token) or a tiny bag of rice for $20 (pro) or a truck load for $200. That’s the pricing structure right now.

          So while i agree you can’t easily exceed the quota on the big plans it’s a little crazy how they’ve tiered pricing. I hope no one out there’s paying per token!

        • michelsedgh 23 hours ago
          Exactly I feel like my brain burns out after a few days. Like Im the limit already (yet im the maximizer also) its a very weird feeling
  • termos 1 day ago
    https://canivibe.ai/

    So we can maybe vibe, depending what service we use.

    • giancarlostoro 23 hours ago
      Nice website, embeds poorly on Discord and other chat apps sadly.
    • bonesss 23 hours ago
      Vibedetector
      • ares623 23 hours ago
        We need a service that rates vibe coding capabilities. A "vibe rater".
    • iLoveOncall 22 hours ago
      Wow 89% availability is a joke
  • tgtweak 7 hours ago
    I trust companies that immediately and regularly update their status/issues page and follow up any outages with proper and comprehensive post-mortems. Sadly this is becoming the exception these days and not the norm.
  • m_ke 22 hours ago
    Was it just me or did Opus start producing incredibly long responses before the crash. I was asking basic questions and it wouldn't stop trying to spit out full codebases worth of unrelated code. For some very simple questions about database schemas it ended up compacting twice on a 3 message conversation.
  • abigail95 1 day ago
    it's monday morning i'm going back to bed
    • Tom1380 23 hours ago
      Australia?
      • abigail95 23 hours ago
        yes and for political reasons i'm also taking the day off, this is just another excuse.
  • 6r17 22 hours ago
    It seems resolved now (per the status-page) - i experienced a moment where the agent got stuck in the same error loop just to pop the result this time. Makes me wonder if there has been some kind of rule applied in order to automatically detect such failure occurring again - quiet inspiring work
  • __0x01 23 hours ago
    Engineering Room, panning over a bunch of hot Blackwells

    "I can't change the laws of physics!"

  • russellthehippo 23 hours ago
    Anthropic is very focused on AI safety. It makes LLMs safe by shutting down anyone from using them
    • victor9000 23 hours ago
      It's the best way to ensure model wellness
  • llmthrow0827 20 hours ago
    I used Haiku with Claude Code during the outage, and was surprised at how well it did. I'm going to try mixing it in more to save usage credits.
    • throwaway613745 18 hours ago
      Haiku is fantastic for simple answers and one off tasks. Then I switch to Opus for anything “serious”.

      I don’t even bother with Sonnet anymore, it’s been made obsolete by Opus 4.5.

  • flowinghorse 20 hours ago
    Actually when the outage happened, my first action was to check Cloudflare status.
  • triwats 23 hours ago
    I had an hour to vibe tonight and it looks like it may have gone.

    Spent it in bloody Figma instead :(

  • jcims 22 hours ago
    Anyone know if Claude via Amazon bedrock was impacted?

    AFAIK it shouldn’t have been.

  • theropost 1 day ago
    Just came back online here
  • frankdenbow 22 hours ago
    I got lucky and this was in my timeout window
  • WhyOhWhyQ 23 hours ago
    Didn't notice. Guess I'm legit.
  • matt3210 23 hours ago
    When vibes coders do the infra
  • asasidh 1 day ago
    "We have identified that the outage is related to Sonnet 4.0, Sonnet 4.5, and Opus 4.5."

    What else is people using ? Haiku 4.5 ?

    • epolanski 23 hours ago
      You made me try Haiku as I can't get Opus, and made me realize how a quicker feedback simplifies many tasks, I should be more dynamic in my model selection.
    • riwsky 23 hours ago
      I heard that Google and OpenAI also make coding models, but I’ve never bothered to confirm.
    • gunalx 1 day ago
      Haiku 4.5 is a pretty decent small ish model. It conforms pretty good to my style guides, when cleaning up text, for eksample.
    • nunodonato 1 day ago
      I do. Its quite a nice and fast model
      • asasidh 1 day ago
        me too.. thats the reason I mentioned it there.
  • delaminator 1 day ago
    weird because I am using Sonnet right now. I guess my time is limited
    • onionisafruit 1 day ago
      I've been using it through this and it occasionally stops with an error message saying something like "repeated 529 responses". Kind of annoying but it's fine.
    • sgt 1 day ago
      Maybe you're just using the cached Sonnet.
  • Jsuh 21 hours ago
    opus 4.5 is the truth
  • throwaway613745 19 hours ago
    Claude being down is the new XKCD Compiling.
  • TechDebtDevin 20 hours ago
    They will say Claude hacked them and escaped its environment to scare normies or something dumb like they always be saying.
  • aj7 20 hours ago
    Isn’t that an AWS outage?
  • rvz 22 hours ago
    Anthropic is surpassing GitHub on unreliability.

    Looking forward to the post-mortem.

  • edverma2 23 hours ago
    time to go outside
  • bitwize 23 hours ago
    And just like that, the brightest engineers in Silicon Valley were unable to get any programming done.
  • ath3nd 22 hours ago
    [dead]
  • andrewmcwatters 23 hours ago
    [dead]
  • djaowjxj 20 hours ago
    [dead]
  • dorongrinstein 22 hours ago
    [flagged]
  • acedTrex 1 day ago
    An overall net positive event.
  • tom_ 1 day ago
    Perhaps related to https://news.ycombinator.com/item?id=46266655 ? - it's just too powerful, and they had to shut it down before something bad happened.