Anthropic Claude and API service outages

(status.claude.com)

40 points | by vikrantrathore 2 hours ago ago

34 comments

  • dannyw 12 minutes ago

    Great reminder to be using multiple providers (i.e. Anthropic 1P, Bedrock, Vertex AI, Azure) with auto-fallback.

    Bedrock has been fine throughout today; just pick two providers and you have much more stable Claude :)

  • alansaber 15 minutes ago

    Yes yes it is key that we vibe code critical infrastructure. I can't wait to see a claude-ism in my next BIOS update.

  • tvbusy an hour ago

    "Coding is solved", how ironic.

  • indrex an hour ago

    How they go down globally? All regions use the same infra?

    • Iolaum 3 minutes ago

      It was a configuration error ...

  • vikrantrathore 2 hours ago

    Anthropic has constant failure since morning.

  • cromka an hour ago

    Anyone can explain why do they fail so often and so seriously? Is this inherent to managing LLMs or is their Ops really just that bad?

    • ifwinterco 27 minutes ago

      Because coding is solved and there’s no need for software engineers any more.

      Being charitable to Anthropic though: coding is sort of solved for a very limited definition of “solved”.

      Software engineering of huge distributed systems at massive scale is very much not solved, and it seems Anthropic don’t have the human capital to do it particularly well

      • nixon_why69 3 minutes ago

        If we want to be even more charitable to Anthropic, they're going from nothing to hyperscaler in like 3 years. I'm as happy as anyone to dunk on the general bubble situation and people claiming their technology is too dangerous to share, then something like this happens, it's hilarious. But it's still actually hard to build a service with that much usage and every org has had some outages on their way to figure it out.

    • Recursing an hour ago

      I think it's because customers don't seem to mind enough to switch.

      I really want to support Anthropic because of their commitments to effective altruism, but it's getting harder and harder to justify on technical merits. Sol is just faster, cheaper, and more reliable, and as good as Opus for my use cases

      • lxgr 25 minutes ago

        > I really want to support Anthropic because of their commitments to effective altruism

        If you're really committed to the ideas of EA, shouldn't you dispassionately select whatever model works best for you, then make as much money as possible using that and donate it? :)

      • jcfrei 18 minutes ago

        I've recently started using codex for most of my coding. Haven't looked back so far: It seems to reason deeper about the code it writes and has much less downtime.

      • nicce 20 minutes ago

        > I really want to support Anthropic because of their commitments to effective altruism

        They are doing the opposite while saying the other. Zero trust about that. They are using every malicious playbook tactic these days to increase users and be more profitable and lock-in the users. Even OpenAI feels better these days.

        • puelocesar 7 minutes ago

          I mean, that’s exactly what “effective altruism” is about? Getting filthy rich and powerful no matter the methods and then the vague promise of doing something good?

      • integricho 40 minutes ago

        Do you actually believe in their altruistic goals?

      • therein an hour ago

        > commitments to effective altruism

        That's a downside if anything.

        • eru 27 minutes ago

          Different folks have different preferences.

          • KingMob 18 minutes ago

            Yes, some people think effective altruism means helping people here and now as efficiently as possible.

            Others think the sheer number of potential sentients in the future justify any amount of suffering tolerated in the here and now.

            Notably, people in the latter group never assume THEY will be the ones suffering for the future.

    • vinni2 an hour ago

      Because they can’t keep up with the demand?

      • moritzwarhier 4 minutes ago

        [delayed]

      • tvbusy an hour ago

        Struggling with demands is a performance problem, not a reliability problem.

        • ACCount37 22 minutes ago

          It is a reliability problem - because if the API ends up rejecting 30% of the incoming queries, no one cares if it's 500 Internal Server Error or 529 Overloaded.

          Having your infrastructure at the knife's edge of load to capacity also means you have no redundancy when something fails.

          • cherioo 14 minutes ago

            If this incident had happened during the day I could buy that argument. But it is happening in the dead of the night. Are there really that much people scheduling claude runs over-night, taking more capacity than day-time? (assume most claude users are west coast programmers)

            My other guess is they are scheduling training runs and their capacity isolation is bad.

        • swe_dima an hour ago

          overly high demand can often put a system in an unstable state

          • therein an hour ago

            Only if you're incapable of throttling to assure quality of service. Are you saying they have so much demand that even their load balancers were overloaded?

            • slopinthebag 34 minutes ago

              There is no point having this discussion. Some people have had their brains genuinely broken by Anthropic and will defend them to the last breath, despite having no clue what they are talking about.

    • vasco 23 minutes ago

      Clearly they just want to be down all the time. They have the ability to throttle down traffic. I have no clue why they decide to throttle it down just enough to have the worst of both worlds, throttling and incidents. Throttle more and have zero incidents, what an incredible revelation.

      • Barbing 10 minutes ago

        They didn’t want to be down so bad they rented capacity from Elon and uptime improved dramatically. Super flaky before that, they were even playing games with response quality to lighten their load nontransparently. Not sure what the issue is today. But on average, past 90 days, good availability and quality right?

    • slopinthebag 35 minutes ago

      Everything is vibe coded, would you expect anything different?

      • alansaber 17 minutes ago

        Quick, release a new claude product then depricate it after 90 days

  • gagan2020 an hour ago

    Mind you, They use latest Anthropic Claude models for programming. /s

  • rvz 40 minutes ago

    One of the Anthropic salesmen told everyone to use loops all over the place, auto mode and use Fable 5 and Opus 5 with multiple sub agents.

    Then it seems they forgot about their own infrastructure which goes down once every two weeks.

    Looks like most of all the engineering knowledge that was needed at Google was lost after the whole org at Anthropic is now vibing their work.

    Rather than screaming “coding is solved!”, “AGI with a month” and spooking everyone with the bogus mysticism of “Mythos” which now everyone has an equivalent strong cyber model, maybe keep the lights on first before plotting the next doomsday story.

    • eru 27 minutes ago

      > Looks like most of all the engineering knowledge that was needed at Google was lost after the whole org at Anthropic is now vibing their work.

      Sorry, what does Google have to do with Anthropic's outage?

  • hyperionultra an hour ago

    Lately Dario has to many bad news from customer side. Of course there is no bad or good news, just marketing, but still…