Elevated errors on Claude Opus 5

(status.claude.com)

34 points | by croemer 2 hours ago

7 comments

  • jcims 10 minutes ago
    Operationally (and anecdotally obv) we've found that accessing Claude via AWS Bedrock has been notably more stable than direct to Anthropic.
    • htrp 2 minutes ago
      We actually tracked this over the last year, bedrock is significantly better than the anthropic direct endpoints
  • jph 27 minutes ago
    Lots of errors. Opus 5 is also giving me many more hallucinations, including things that aren't even in the right territory. It's also telling me that it's making many mistakes, and the language feels off-kilter as if it's not using typical clear phrases.
    • RGS1811 22 minutes ago
      It is aggressively proactive in ways that make it very hard to use. I had to turn down the effort level to “low” to stop it from going off in random directions every couple of turns.
  • Aldipower 1 hour ago
    I would say "Elected errors _in_ Claude Opus 5" wouldn't be incorrect either.. Opus 5 isn't very reliable for coding and introduces a lot of regressions every single time I use it. Do you have the same experiences?
    • flaburgan 40 minutes ago
      I also found it to forget some obvious cases in a quite simple flow (validate the email address of a user who register), that surprised me a lot. Maybe it's because I got used to Fable? But I am quite sure Opus 4.8 wouldn't have make this mistake. If I had time I would try the same prompt with it to see. Anyway, back on 100% Fable for me.
    • jarym 34 minutes ago
      Getting to grips with each new model does require some tweaking and experimentation. So far I've found Opus 5 to repeatedly pause its work and give me some seemingly randomly invented decisions to make.
      • jdthedisciple 3 minutes ago
        > give me some seemingly randomly invented decisions to make

        Any examples?

    • egeozcan 56 minutes ago
      I don't know what I could be doing differently to you but I found Opus 5 to be more reliable than even myself at times. Maybe your stack is unusual or you have conflicting commands in your prompts vs CLAUDE.md (that really confuses it)? It could be anything but this huge error bar in delivered quality is one of the biggest issues with LLMs.
    • Saline9515 31 minutes ago
      Same here, also it lies often to me or implements something else that what was planned. It feels quite strange to see it say casually "I didn't tell you the full truth on X" when I notice the issues. At the same time, maybe it is more honest?
    • benjiro29 1 hour ago
      Opus 5 isn't very reliable for coding and introduces a lot of regressions every single time I use it.

      And GPT 5.6 Sol over engineers just about everything. No LLM is perfect, its about learning the issues with each LLM and figuring out if you can live with it. Knowledge means that you can anticipate if it tries to pull something funny, and harness it against that behavior.

      • Aldipower 59 minutes ago
        Sure, but I am a long time Opus user 4.5,4.6,4.7,4.8 and I wonder what's wrong with 5?
        • pimeys 20 minutes ago
          I remember when 4.7 and 4.8 were released and people were asking what's wrong with them and 4.6 is the best.

          But yes, I also think it's not the greatest model for programming. On the other hand, for agentic tasks that are not programming related it's hard to beat Opus 4.8. It can try different things and pivot even when the user is not great with prompting. 5.0 seems to not be worse, but definitely wastes more tokens and costs more.

          • someguyiguess 3 minutes ago
            4.6 was better in some way that I can’t put my finger on. None of the models since have been able to reproduce its quality of output for me.
      • cyanydeez 1 hour ago
        this would be _Great_ advice if you owned your own LLM and your knowledge was trapped in Amber because you were satisfied.

        It's horrible advice given what we've seen consistent: changing alignments, changing guardrails, changing system prompts, changing inference priorities, etc.

        Anyone who relies on these for their work product is chaining themselves to a matrix multiple of indetermintism.

    • bearjaws 55 minutes ago
      I do not experience any regressions, I don't really notice much difference either.
    • trentor 1 hour ago
      Maybe it's my harness but I haven't seen it introducing regressions.
    • cbg0 1 hour ago
      Do you not have unit tests, or how does it introduce regressions? You can tell it how to run the test suite in CLAUDE.md
      • Aldipower 1 hour ago
        I detect the regression already in planning with Opus 5, so I do not let Opus 5 implement anything. But it is a waste of time and tokens! Does planning with Opus 5 works out for you?
        • cbg0 35 minutes ago
          It sounds like you just need to correct the plan it lays out to avoid the regression? I'm just looking to debug with you, not defending the model. I've mostly used Opus 5 for code reviews & bugfixes.
          • Aldipower 29 minutes ago
            Yeah fine. I mean my plan wasn't to difficult. For example this morning I started with Opus 5 to tackle a problem. During planning at some point Opus 5 detected _8_ regressions in it's own planning, after I directed it towards those potential regressions. So, in this very moment now, Fable 5 implements code already and the planning before with Fable, done with the same instructions, was flawless and quick. And I am sure, Opus 4.8 would be flawless either. Same harness, same claude.md, etc..
      • quaheezle 1 hour ago
        Opus 5 tries to modify the unit tests as a cover to its own regressions - thinking its own logic is correct and the test must be wrongly specified
        • jvuygbbkuurx 31 minutes ago
          I found it eagerly reversing existing product decisions like changing a user given date into created date, since it thought creating something that is in the past is incorrect. This was not even related to the task at hand at all. I noticed this kind of stuff happens more with ultracode for some reason.
          • grim_io 0 minutes ago
            Any subagents-based workflow is prone to this, because of the fragmented context(by design).
      • simiones 1 hour ago
        It is a well known fact that projects with unit tests never have regressions.
        • cbg0 38 minutes ago
          I don't understand the need for the snarky comment, LLMs can run the test suite and avoid regressions.
          • simiones 0 minutes ago
            A change can introduce regressions in any large project even if 100% of unit tests pass. Unit tests test individual units, regressions can happen at many levels. Especially if we treat performance degradations as regressions.
        • cyphar 39 minutes ago
          [dead]
  • ectoloph 37 minutes ago
    These bursts of downtime are one of the reasons I end up with multiple smaller subscriptions between providers.

    I'd just end up being really annoyed about the downtime if it lands in the middle of a working day.

    • oefrha 14 minutes ago
      Not sure if it’s just me but in Codex, GPT-5.6-Sol and IIRC older 5.5 models can stop dead in the track a couple times a day saying “model is at capacity” (paraphrasing). Then I wait a minute or two and ask it to continue and it’ll more often than not happily use the same model. These frequent mini “outages” are pretty annoying especially if one isn’t supervising. Claude has had long outages but I haven’t run into this kind of mini outages on a daily basis recently.
      • nijave 0 minutes ago
        I wish the harnesses would auto resume but I suppose that would also add more load without more money for subscription customers...
      • someguyiguess 4 minutes ago
        That happens to me constantly with codex
  • croemer 2 hours ago
  • Invictus0 27 minutes ago
    stop posting these on hn
    • darkwater 22 minutes ago
      There are tens of HN front page posts about GitHub outages. Why not Anthropic's?
  • ojinai 6 minutes ago
    [flagged]