Elevated errors on Claude Opus 5 • Hacker News Board

Re: Elevated errors on Claude Opus 5

#11

Post by Aldipower » Mon, Jul 27, 2026, 12:33 PM UTC

benjiro29 wrote: post #8

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?

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.

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?

Re: Elevated errors on Claude Opus 5

#12

Post by egeozcan » Mon, Jul 27, 2026, 12:36 PM UTC

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?

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.

Re: Elevated errors on Claude Opus 5

#13

Post by bearjaws » Mon, Jul 27, 2026, 12:37 PM UTC

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?

I do not experience any regressions, I don't really notice much difference either.

Re: Elevated errors on Claude Opus 5

#14

Post by flaburgan » Mon, Jul 27, 2026, 12:52 PM UTC

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?

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.

Re: Elevated errors on Claude Opus 5

#15

Post by cyphar » Mon, Jul 27, 2026, 12:53 PM UTC

simiones wrote: post #7

cbg0 wrote: post #4

Earlier quoted context omitted.

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

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

[dead]

Re: Elevated errors on Claude Opus 5

#16

Post by cbg0 » Mon, Jul 27, 2026, 12:54 PM UTC

simiones wrote: post #7

cbg0 wrote: post #4

Earlier quoted context omitted.

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

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.

Re: Elevated errors on Claude Opus 5

#17

Post by ectoloph » Mon, Jul 27, 2026, 12:55 PM UTC

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.

Re: Elevated errors on Claude Opus 5

#18

Post by cbg0 » Mon, Jul 27, 2026, 12:57 PM UTC

Aldipower wrote: post #5

cbg0 wrote: post #4

Earlier quoted context omitted.

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

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?

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.

Re: Elevated errors on Claude Opus 5

#19

Post by jarym » Mon, Jul 27, 2026, 12:58 PM UTC

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.

Re: Elevated errors on Claude Opus 5

#20

Post by jvuygbbkuurx » Mon, Jul 27, 2026, 1:01 PM UTC

quaheezle wrote: post #6

cbg0 wrote: post #4

Earlier quoted context omitted.

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

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.