Birbla

Join the discussion

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

Sign in
  • Hacker News
  • Out of my 7 simultaneous sessions (my usage limit reset is tomorrow, so I have some lesser important projects to use my tokens on) there is still 1 session purring on. So there's at least 1 little Claude server still running.
    by skerit
  • They are going to reset the weekly limit before your weekly limit. Mine resets tomorrow too.
    by a_c
  • This is where you figure out how to use the other ones, right?

    Someone tell me how to ChatGPT my VSCode! ;)

    by bombcar
  • https://learn.chatgpt.com/docs/codex/ide

    I've actually never looked before, but look at how user friendly that is, compared to the claude page [2]. I swear the documentation writers at OpenAI maybe, actually, use their own documentation!

    [2] https://code.claude.com/docs/en/platforms

    by nomel
  • Probably just as well with how terrible Opus 4.8 has been for me lately. I'm sure it's a common thing to complain about the latest model being nerfed, but I've legitimately never experienced such a drastic cliff in Claude's quality and a rise in its hallucinations and basic comprehension errors since upgrading. The few days I experimented with Fable also weren't much more promising. Has anyone coined a term yet for the likelihood of newer models getting worse as the AI-generated content they get trained on starts to approach critical mass? If Anthropic isn't already thinking hard about a solution, they probably should be.
    by hashim
  • Do you guys think this is related to Azure coming out with a 43% increase this quarter? Motivating Anthropic to move to another cloud provider?
    by la1n
  • Sorry it was me. I asked it what the last number of Pi is.
    by peterspath
  • Next time, maybe ask for the second to last!
    by nomel
  • Interestingly the Claude for government is up with 99.99% uptime according to the graph.
    by tyfon
  • Well, iranian schools don't bomb themselves after all..
    by metropolis_pt2
  • That one is not public and if it goes down can be hidden, so they can hardcode the value and call it a day.
    by hoppp
  • Let me guess: it went rogue and hacked itself
    by q8zd3
  • How does this help their PR?
    by robofanatic
  • Claude always seems unreliably lately. Output and reasoning have become very inconsistent even on good days. I'm actually feeling more productive now that it's down.
    by danielfoster
  • Flirting with one 9 of reliability http://status.claude.com/
    by seizethecheese
  • From the company that has solved coding.
    by denverllc
  • They can still target four nines (0.9999)
    by winrid
  • Forget five nines, our new goal is to be better than nine fives.
    by walrus01
  • did the uptime go up instead of down during the outage?

    thought I saw 99.36% and 99.35% more than an hour ago - now it's up at 99.43%

    edit: funny thing, my phone shows 99.29% uptime for "claude.ai" while my PC shows 99.43% at the same time (2x Firefox).

    edit2: seems like the percentage changes based on the width of the screen

    by tcfhgj
  • Not fair, I count 3 whole nines in "99.49 % uptime"
    by mpwoz
  • I remember when "as reliable as GitHub" would have been a compliment
    by vitally3643
  • AI is a technology for removing nines from uptime, and adding them to Sturgeon's law.
    by cobbal
  • Quite sad, their models are great but their uptime seems to be the worst in the competition.
    by garo-pro
  • Anthropic is careful about buying capacity, and too conservative given their explosive growth. That compares favorably with OpenAI and its Monopoly money Ponzi scheme approach, which will blow up sooner or later.
    by fmajid
  • It is because unlike Kimi, they are not honest about capacity. They just oversell.
    by therein
  • As someone at 96% 2 days into their Max subscription, my totally unbiased opinion is that these errors warrant a full usage reset.
    by dahdum
  • It's only fair.
    by mcfdoesdev
  • It's Anthropic's way of making sure you're spreading out your usage :)
    by luciandan
  • You should definitely explore caveman repo and other token-saving repositories. I’m currently at a maximum of 5X and have rarely exceeded 80% of my weekly limits.
    by alvink1212
  • Codex prompt before i go to sleep:

    Every five minutes, check https://status.claude.com/. If the issue has been resolved, resume the Claude sessions running in the tmux sessions named session2, session3, and session7

    by kmetan