Elevated errors on Claude Opus 5 • Hacker News Board

Re: Elevated errors on Claude Opus 5

#11

Post by o10449366 » Mon, Jul 27, 2026, 12:30 PM UTC

rich_sasha wrote: post #3

I've noticed something else - as Anthropic models get even more and more superhuman, they seem to serve me more and more casual nonsense. Not like adding glue to pizza. Here's an example from today (paraphrasing): "you need to run `git merge-base branch1 branch2`. Pay attention to the order of arguments, it is important: `git merge-base` is symmetric and returns the same value regardless of the order of inputs". So w…

Claude has always noticeably degraded under heavy load. Opus goes from "decent to work with" to "dumb intern" depending on whether you're working at 3 AM west coast or 10 AM - 5 PM. It's part of why I cancelled my subscription - "max" plans and "extra high" effort are meaningless when there's so much variability between model availability, model performance, and harness bugs every day and every week.

Re: Elevated errors on Claude Opus 5

#12

Post by wongarsu » Mon, Jul 27, 2026, 12:32 PM UTC

rich_sasha wrote: post #3

I've noticed something else - as Anthropic models get even more and more superhuman, they seem to serve me more and more casual nonsense. Not like adding glue to pizza. Here's an example from today (paraphrasing): "you need to run `git merge-base branch1 branch2`. Pay attention to the order of arguments, it is important: `git merge-base` is symmetric and returns the same value regardless of the order of inputs". So w…

I've noticed the same pattern even in GLM5.2. It has always been a thing, but it seems to be getting worse in recent models

It does feel like the kind of thing beam search would fix. The LLM starts the sentence with a claim like "Pay attention to the order of arguments". Around that time it "notices" that the order doesn't matter, but it's already committed to the sentence and has to complete it in the best way still possible

Maybe at some point someone figures out how to train models with a backspace token

Re: Elevated errors on Claude Opus 5

#13

Post by brookst » Mon, Jul 27, 2026, 12:32 PM UTC

rich_sasha wrote: post #3

I've noticed something else - as Anthropic models get even more and more superhuman, they seem to serve me more and more casual nonsense. Not like adding glue to pizza. Here's an example from today (paraphrasing): "you need to run `git merge-base branch1 branch2`. Pay attention to the order of arguments, it is important: `git merge-base` is symmetric and returns the same value regardless of the order of inputs". So w…

I don’t find Sonnet usable at all. Especially for the price. I’d much rather get half the usage of Opus.

Re: Elevated errors on Claude Opus 5

#14

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

So, how's the OpenAI situation? Is the grass greener on the other side?

Re: Elevated errors on Claude Opus 5

#15

Post by seunosewa » Mon, Jul 27, 2026, 12:45 PM UTC

matheusmoreira wrote: post #14

So, how's the OpenAI situation? Is the grass greener on the other side?

GPT 5.6 Sol is so free of drama for me for brainstorming, writing prompts, etc. Tasks I always did with Opus until 4.7.

Re: Elevated errors on Claude Opus 5

#16

Post by vintagedave » Mon, Jul 27, 2026, 12:56 PM UTC

matheusmoreira wrote: post #14

So, how's the OpenAI situation? Is the grass greener on the other side?

Yes. I switched to Codex some time ago. I feel like I get fewer outages (had one over the weekend), and coding results are good. I built my own agent harness using OpenAI models too and feel it was the right decision.

Re: Elevated errors on Claude Opus 5

#17

Post by rvz » Mon, Jul 27, 2026, 1:13 PM UTC

ACCount37 wrote: post #9

rvz wrote: post #6

Claude decided to take an extra day off, after going on vacation yesterday [0] and when Codex went and took a longer break the day before that. No wonder the amount of water that both Claude and Codex are taking they also need so many frequent hydration breaks. [0] https://news.ycombinator.com/item?id=49056739

Can we not do the "AI is drinking all the water" bullshit at least on HN?

There are many sources that already document it being true so we both know it is not bullshit. [0][1][2]

So you think that the water that comes out of these data centers is safe for humans once released and the mass consumption of them is not a concern?

Sounds like a way to sweep this environmental issue under the rug.

[0] https://theoec.org/news-and-information/behind-the-data-boom...

[1] https://fieldreport.caes.uga.edu/publications/TP121/how-data...

[2] https://www.wsj.com/tech/ai/ai-data-centers-water-use-901e29...

Re: Elevated errors on Claude Opus 5

#18

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

ACCount37 wrote: post #9

rvz wrote: post #6

Claude decided to take an extra day off, after going on vacation yesterday [0] and when Codex went and took a longer break the day before that. No wonder the amount of water that both Claude and Codex are taking they also need so many frequent hydration breaks. [0] https://news.ycombinator.com/item?id=49056739

Can we not do the "AI is drinking all the water" bullshit at least on HN?

If you want a safe space, try the Fox New comments.

Re: Elevated errors on Claude Opus 5

#19

Post by zhoBEENG » Mon, Jul 27, 2026, 1:42 PM UTC

wongarsu wrote: post #12

rich_sasha wrote: post #3

I've noticed something else - as Anthropic models get even more and more superhuman, they seem to serve me more and more casual nonsense. Not like adding glue to pizza. Here's an example from today (paraphrasing): "you need to run `git merge-base branch1 branch2`. Pay attention to the order of arguments, it is important: `git merge-base` is symmetric and returns the same value regardless of the order of inputs". So w…

I've noticed the same pattern even in GLM5.2. It has always been a thing, but it seems to be getting worse in recent models It does feel like the kind of thing beam search would fix. The LLM starts the sentence with a claim like "Pay attention to the order of arguments". Around that time it "notices" that the order doesn't matter, but it's already committed to the sentence and has to complete it in the best way still…

Diffusion language models do this. I’d guess they are the future.

Re: Elevated errors on Claude Opus 5

#20

Post by croemer » Mon, Jul 27, 2026, 1:45 PM UTC

And here we go again, new incident started at 13:39 UTC: https://status.claude.com/incidents/rkk5x44tndw9

Third outage today. Per https://downdetector.com/status/claude-ai/ the people affected grows every time: first one had peak 19 reports, second 24 and now it's already 39.