Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Elevated errors on Claude Opus 5

status.claude.com

Post reply on HN
Print view View original

31–40 of 79 posts

Re: Elevated errors on Claude Opus 5

#31

Post by someguyiguess »

oefrha wrote: post #28
ectoloph wrote: post #17

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.

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 th…

That happens to me constantly with codex

Re: Elevated errors on Claude Opus 5

#32

Post by someguyiguess »

pimeys wrote: post #27
Aldipower wrote: post #11

Earlier quoted context omitted.

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?

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…

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.

Re: Elevated errors on Claude Opus 5

#33

Post by jdthedisciple »

jarym wrote: post #19
Aldipower wrote: post #3

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?

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.

> give me some seemingly randomly invented decisions to make

Any examples?

Re: Elevated errors on Claude Opus 5

#34

Post by htrp »

jcims wrote: post #29

Operationally (and anecdotally obv) we've found that accessing Claude via AWS Bedrock has been notably more stable than direct to Anthropic.

We actually tracked this over the last year, bedrock is significantly better than the anthropic direct endpoints

Re: Elevated errors on Claude Opus 5

#35

Post by grim_io »

jvuygbbkuurx wrote: post #20
quaheezle wrote: post #6

Earlier quoted context omitted.

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

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.

Any subagents-based workflow is prone to this, because of the fragmented context(by design).

Re: Elevated errors on Claude Opus 5

#36

Post by simiones »

cbg0 wrote: post #16
simiones wrote: post #7

Earlier quoted context omitted.

It is a well known fact that projects with unit tests never have regressions.

I don't understand the need for the snarky comment, LLMs can run the test suite and avoid regressions.

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.

Re: Elevated errors on Claude Opus 5

#37

Post by nijave »

oefrha wrote: post #28
ectoloph wrote: post #17

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.

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 th…

I wish the harnesses would auto resume but I suppose that would also add more load without more money for subscription customers...

Re: Elevated errors on Claude Opus 5

#39

Post by cbg0 »

Aldipower wrote: post #22
cbg0 wrote: post #18

Earlier quoted context omitted.

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.

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 s…

Do you think it might be overthinking? Try it on medium effort.
Post reply on HN