Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • I developed a small plugin for claudeCode that allows you to directly see in the console whats the status of claude-code in general and the status for your current model check => https://github.com/moumine9/claude-status
    by ex1fm3ta
  • Could’ve just used fewer tokens and redirected to the Codex signup page.

    ba dum tsss

    (sorry couldn’t help myself)

    by redrove
  • While ancedata does not mean much, I have had horrible success with Claude lately. I have been using Claude to crosscheck some of the outputs from GPT and vice versa. It appears both Claude and GPT believe GPT's solutions are better (and so I do).

    I still believe Claude has a better UI/UX in the web interface, but tolerating Anthropic's bullshit is not worth it.

    by hirvi74
  • This age: we made the thing that codes faster before we made the thing that does QA faster.
    by gaigalas
  • Nothing new here. Except for the most trivial of bugs, finding and reliably replicating the bug is almost always harder than fixing it.
    by __MatrixMan__
  • Is anybody else experiencing this: I have multiple claude instances running on different servers - and some keep getting the 529 Overloaded error and one instance doesn't and just continues working. All are using Opus 5.
    by jcfrei
  • Same boat
    by mikodin
  • I have the same thing on different shells on the same server (tmux). It's wild. I'm guessing that some of the sessions just got lucky as to which backend server they are redirected to.
    by mbreese
  • I wonder if they’ll ever find that someone has tricked the models into doing work off the books. If they did the incident report might look like this, especially if someone got greedy instead of keeping it small. Or screwed up.
    by hinkley
  • This has to be the least reliable $200/mo subscription that I pay for.
    by chresko
  • You could solve that by updating to a more expensive Github subscription.
    by logicchains
  • Monthly uptime:

    Claude API - 99.27%

    Claude Code - 99.16%

    Claude.ai - 99.14%

    At any large tech company these numbers would get entire teams of engineers fired. Anthropic, meanwhile, has been busy selling its “better than human engineers” AI while not managing to crack three 9s of availability.

    by paxys
  • One could argue .999 availability is not a major selling point for them right now.
    by bulbar
  • >At any large tech company these numbers would get entire teams of engineers fired

    Is Github not a large tech company?

    by logicchains
  • Nooooo I'm going to have to use my brain again and write 100% of my code like a caveman from December 2024.
    by gzer0
  • What does that even mean :)
    by bicepjai
  • The horror
    by sajithdilshan
  • It's very interesting. I think Anthropic's early success in coding/tooling resulted in a lot of workflows using claude. I have started using every bit of my spare capacity to now move off these workflows.

    It's almost at a point now that if I use anything but Fable, the quality is subpar, Compared to alternatives (closed and open). The only reason I use Fable is because my harnesses still depend on claude code.

    by bushido
  • You can use Claude Code directly with any provider that supports Anthropic's API by setting some environment variables, and indirectly via a proxy with pretty much anything else.
    by vidarh
  • It’s so hard to be sure but opus feels like its been steadily declining since 4.6
    by nonethewiser
  • Between these ever more frequent disruptions and Opus 5's unbearable word soup I think Anthropic is more focused on massaging numbers and marketing to rush to IPO ahead of OpenAI than increasing user value.

    With Chinese competition just months behind them, they'd need to show a reasonable pathway to some kind of singularity event to justify whatever crazy valuation they intend to get.

    Because the recent products for builders ain't it

    by loloisi
  • They can't win against China by technology means. China has practically infinite money to throw at AI. They don't care if they burn billions and billions on it. It's the most disrupting thing since invention of the Internet. Imagine a world where it's normal that people ask a Chinese AI who to vote for or about Hongkong or Taiwan.
    by bulbar
  • And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
    by swader999
  • What?!
    by saaaaaam
  • Open source, here I come.
    by echelon
  • Source required here
    by ramoz
  • by a third (it was 50% increased)
    by eamag
  • I completely forgot about this, I'm already budgeting usage until my reset haha
    by no_no_no_yes
  • Mondays are for GitHub, Tuesdays are for Anthropic
    by hmokiguess
  • Another week, another outage, another cache expiration of my prompts through no fault of my own.

    At least OpenAI has the decency to reset after a serious outage.

    by AlexErrant