Ask HN: Is Claude down again?

84 points | by coderbants 17 hours ago ago

71 comments

  • rethab 17 hours ago ago

    Same issue here. What was the name of that question and answer site again where you had to manually copy and paste code from? ;-)

    Official status is still green: https://status.claude.com/

    But downdetector is clear: https://downdetector.com/status/claude-ai/

    /edit: there's an official incident now: https://status.claude.com/incidents/jm3b4jjy2jrt

    • giancarlostoro 16 hours ago ago

      They just updated it some 4 minutes ago.

      > Update - We're currently investigating issues with Claude Code and Claude.ai. Some users may be unable to log in, and others may experience slower than usual performance. The Claude API is not affected.

    • buddhistdude 16 hours ago ago

      oh about that one... we killed it unfortunately

    • Lionga 14 hours ago ago

      vibe coded trash....

  • izolate 16 hours ago ago

    Does anyone recall how to code manually? I certainly don't :-)

    • thrill 16 hours ago ago

      I do - but then I shudder, and go make a sandwich - which still needs me for the moment.

      • pan69 12 hours ago ago

        What? You don't just prompt your kitchen?

        • pixl97 12 hours ago ago

          sudo make me a sandwich

    • siva7 16 hours ago ago

      I also don't recall what i'm going to do tomorrow as busy as i am. That's what calendars are for.

    • Hamuko 16 hours ago ago

      The C-suite doesn't want us to write code by hand anymore, so I think I'm supposed to just drink tea and collect salary whenever Claude is down.

    • behnamoh 16 hours ago ago

      I feel ashamed writing code while Claude does it way better than me... I've found my forte is at designing systems and making project-level decisions, something that Claude still doesn't do very well.

      • taylorius 9 hours ago ago

        Forte of the gaps :-) I'm exactly the same.

  • lnenad 17 hours ago ago

    It's really amazing how stability of platforms has gone down in the last year or so.

    • romanhn 16 hours ago ago

      If only this was correlated with something else going on in the industry...

    • khuedoan 7 hours ago ago

      > 100% of our code is written by AI

      Yeah we can tell...

    • erksa 16 hours ago ago

      yes, the new normal is crazy. Claude/Github et al.

      They are dogfooding their own tools and causing so much downtime, all in the spirit of "staying a head".

    • Ancalagon 13 hours ago ago

      The schadenfreude is so fucking palpable

      • ramon156 12 hours ago ago

        Weird take, will you also look sour at devs who use local LLM's in ~50 years? Or is that different

    • skeledrew 15 hours ago ago

      The mass immigration probably still taking a toll.

  • garethsprice 11 hours ago ago

    Working for me (Desktop + Code) but had a bunch of oauth issues this morning and it's been up and down like a drunken monkey on a trampoline all week, especially around start of biz times in the US.

    The Pentagon spat is having a hell of a Streisand Effect on them; DAUs +180% (source: SimilarWeb), paid subs doubling. If past experience is any indicator, it'll settle down as they scale up (or they fall out of the news cycle). Google Trends search interest shows the story: https://trends.google.com/explore?q=claude%2Canthropic&date=...

  • eduardogarza 15 hours ago ago

    Can someone that's worked at one of these big companies honestly explain how it happens that when these guys are down, it's never for like 10-15 mins ... it's always 1-2+ hours? Do they not have mechanisms in place to revert their migrations and deployments? What goes on behind the scenes during these "outages"?

    • aix1 15 hours ago ago

      Part of it observability bias: longer, more widespread outages are more likely to draw signficant attention. This doesn't mean that there aren't also shorter, smaller-scope outages, it's just that we're much less likely to know about them.

      For example, if there's a problem that gets caught at the 1% stage of a staged rollout, we're probably not going to find ourselves discussing it on HN.

    • jcfrei 15 hours ago ago

      Quick fixes have tendencies to break other stuff and just make matters worse. Better to leave it offline for a little longer, fix the definitive root issue and make sure it comes online nicely. If the issue was just a quirk in a recent deployment then these probably can be reverted easily on the endpoints where they were just deployed (I'm sure they are using staggered roll-outs). These long term downtime things are probably not issues related to a recent release.

    • Ocerge 14 hours ago ago

      You will run into thundering herd/hotspotting/pre-warmed caching issues when you have to restart. There's generally not an easy to way to switch these sorts of systems on and off, especially a relatively new system that isn't battle-hardened.

      I got nothing for the github outages this year though, that seems like incompetence.

    • mrguyorama 12 hours ago ago

      Well when the coding agents go down who are they supposed to ask what the problem is?

      They should probably buy subscriptions to those Chinese agents.

  • HPSimulator 11 hours ago ago

    I ran into this with my own SaaS a while back.

    One day I started getting API errors across requests and initially assumed it was something on my side. After digging into it, the provider I was using was getting overloaded and intermittently failing.

    That was the moment I realized relying on a single external service was a risk I hadn’t really planned for.

    Now I keep two providers configured: a primary and a secondary. If error rates spike or the API stops responding, the system can fail over instead of the whole product going down.

    It added a bit of complexity, but the peace of mind is worth it.

  • bartread 16 hours ago ago

    I don't know about down but I use the VS Code extension on a Pro plan (that I'm considering upgrading from) and it's been slower than molasses flowing uphill in winter for me this afternoon. I'm (a) feeling unwell, and (b) up against a deadline, so this is starting to damage my calm.

  • valdezm 16 hours ago ago

    Yes they are down --

    /login

    ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── Login

       OAuth error: timeout of 15000ms exceeded
    
    
       Press Enter to retry.
    
      Esc to cancel
  • avra 17 hours ago ago

    I was wondering the same. They just updated the status page but it was showing green for a while and I couldn't login.

    https://status.claude.com/

    • coderbants 17 hours ago ago

      The issues have been described as login/logout, but I'm not sure that's all that's happening. In today's outage and the last the API stopped and kicked the session out.

      I only mention this in case someone from Anthropic perhaps isn't aware that it seems to be a wider issue than login/logout (although I'm sure they are!)

    • behnamoh 16 hours ago ago

      Weird because it shows green but obviously things aren't working.

    • verelo 16 hours ago ago

      Jesus that’s a bad looking status page lol it’s almost a rainbow

  • astatine 16 hours ago ago

    Same issue. Getting an "internal server error" message

  • throwaway89201 16 hours ago ago

    I use Big-AGI [1] as selfhosted open source LLM workspace, and it's quite telling that when adding API keys for Anthropic, it presents a note inbetween reading "Experiencing Issues? Check Anthropic status" that it doesn't for any other model provider.

    [1] https://github.com/enricoros/big-AGI (no affiliation)

  • iamsaitam 14 hours ago ago

    Login failed: Request failed with status code 500

    Good times..

  • throwa356262 11 hours ago ago

    Maybe unrelated but Claude has not only been slow but quality has also been bad the last 3-4 days.

    Everything was fine last week then suddenly even the smallest tasks can't be completed correctly

  • zurfer 16 hours ago ago
  • mervz 16 hours ago ago

    Time for all of the cosplaying developers to sit around and twiddle their thumbs.

  • prmph 16 hours ago ago

    Are they going to extend my subscription time as a result? It ends today, but I was locked out an hour or so ago, and I'm not sure if that was actually due to this outage.

    All the vibe coding is clearly not working out too well.

  • kush0505 17 hours ago ago

    Experienced same... they logged me out on claude code a few minutes ago. And when I login, it makes me wait >15000ms for the auth (which exceeds their cutoff time), so auth fails!

  • ridiculous_leke 16 hours ago ago

    Can people drop a good LocalLlama setup that I can run on M4?

    • giancarlostoro 16 hours ago ago

      Not sure about LocalLlama, but have you tried LMStudio? If you use Zed it will auto-pickup whatever model you enable on LMStudio. I keep meaning to write a blog post about this for people unaware that you can pair the two pretty easily on a Mac. I mostly use CC but like to test offline models now and then to see how far they've come along.

      • ridiculous_leke 15 hours ago ago

        I use Ollama to run local models but have never used one with CC. Curious what models work best for people.

        • giancarlostoro 14 hours ago ago

          I use Zed with its Claude Code integration, and if I wanna use any other LLM I use LMStudio which is nice on the Mac, and hosts the APIs for it, Zed knows which models are available which is a plus.

  • skeledrew 15 hours ago ago

    Looks like I'm debugging this issue myself.

  • epolanski 16 hours ago ago

    Slightly ot but I've been using OpenAI's GPT 5.4 on Codex and so far finding it more convincing than Claude with Opus 4.6 at maximum thinking for my use cases.

    I'm more interested in helping with design and architecture rather than having it author tons of code.

    Keep in mind that OpenAI has a way more generous tier for 20$ than Anthropic's one, and I think you can even use codex for free with the latest models, so give it a shot, you may find it better than you expected and a solid backup to Claude.

    • pgm8705 16 hours ago ago

      I agree it seems better at complex work. However, I find that it often tries to make ALL work complex. I had a simple bug fix where I knew exactly what the 1-2 line fix was. GPT 5.4 added like 200 LOC and started refactoring the entire function of the app. Was the refactor possibly an improvement? Maybe, but I needed the fix quick so I stopped it and switched to Claude, which did exactly what I was expecting.

      • aroman 15 hours ago ago

        Perfectly mirrors my own experience.

  • anonfunction 16 hours ago ago

    I can't login to my subscription

  • xeornet 16 hours ago ago

    Auth is failing, session kicked out.

  • world2vec 16 hours ago ago

    Weird, it' all looks good to me. Using both Chat and Code variants without issues.

    • minton 16 hours ago ago

      Same. I have been using it all morning, no issues.

  • gku 15 hours ago ago

    oauth `redirect_url` points to localhost, so the login redirect hangs

    • Lionga 14 hours ago ago

      claude code fully vibe coded confirmed

    • odshoifsdhfs 14 hours ago ago

      please please please tell me this is real

      because if it is, god, I'm done with this industry. just done. I rather sell my toenail clippings for scraps of food than deal with this shitty insanity

  • eduardogarza 17 hours ago ago

    Authentication down for me

    • sgt 16 hours ago ago

      Same here.. I try to log in (via Google) and it just stops me at the "Authorize" step.

  • Dead_Last 16 hours ago ago

    Same here:

    OAuth error: timeout of 15000ms exceeded

    Press Enter to retry.

  • djohnston 11 hours ago ago

    coding is largely solved - a soundbite that will live in infamy

  • aeblyve 16 hours ago ago

    I found it absurdly slow yesterday.

  • messh 16 hours ago ago

    It's down for me

  • Shadow-CTO 15 hours ago ago

    claude looking for that $500k salary, too

  • Dead_Last 16 hours ago ago

    Yep same here:

    OAuth error: timeout of 15000ms exceeded

    Press Enter to retry.

  • armandososa 14 hours ago ago

    Looks like it is back.

  • UncleOxidant 16 hours ago ago

    seems to be.

  • behnamoh 16 hours ago ago

    Yup, I get:

        OAuth token has expired. Please obtain a new token or refresh your
         existing token.
    
    And their /login page doesn't work.

    claudown

  • Shadow-CTO 15 hours ago ago

    woohoo, break time!

  • benzible 17 hours ago ago

    Nope. Me too.

  • devadjacent 16 hours ago ago

    It's down. I hate this