Elevated error rates on Opus 4.7

rrob about 2 hours ago 42 commentsRead Article on status.claude.com

⚡ Community Insights

Discussion Sentiment

77% Positive

Analyzed from 952 words in the discussion.

Discussion (42 Comments)Read Original on HackerNews

lepuski•about 2 hours ago

I can't see why anyone still chooses Claude. Codex outperforms it in most respects, and its quotas are about ten times larger. A $100 Codex plan gets me through the whole week with 6–12 hours of coding per day.

jjice•about 1 hour ago

I found GPT 5.5 is pretty solid, but I keep getting impressed by opus. It's tracked down some insane stuff while I look away during a meeting. 5.5 is way closer than previous OpenAI models to Anthropic IMO.

These things are so tricky because everyone has a seemingly conflicting experience. Part of the fun I guess!

SatvikBeri•about 1 hour ago

I've never actually run into the issues that people talk about online, like Claude suddenly getting dumb or running out of usage. So there's just not a lot of incentive for me to shop around. I've used Amp a bit, and it's quite nice, but a bit more expensive without the subsidized subscription.

gardnr•about 1 hour ago

Are you using Opus? Sonnet remains as useful as it was while Opus efficacy and token burn rate has soured over the last 4 months.

fny•37 minutes ago

I'm using Opus on xhigh 10+ hours a day, and I've only reached 80% of weekly limits when doing massive ports or refactors. I haven't once hit hourly limits, and I've used Claude very, very aggressively. I guess its a pain point for power users.

raincole•26 minutes ago

It has always been like this. We actually know that the model performance has been mostly steady[0], but you cannot beat the notion of "evil companies secretly serving us worse models." The meme value is too strong.

[0]: https://marginlab.ai/trackers/claude-code/

mbreese•35 minutes ago

When do you use it the most? I’ve noticed that it most often starts to degrade during 10-5 US East coast time. Late at night, I have the least amount of issues, but without fail, if I’m trying to do anything complex during the day, Claude gets loopy.

dboreham•about 1 hour ago

Same here. Works every time. Never ran into usage limits either.

hansvm•about 1 hour ago

Claude is the only AI coding tool I've found worth a damn. Without it I'd just do everything by hand save for a few bash scripts or whatever.

arcanemachiner•37 minutes ago

Have you tried other harnesses, such as OpenCode?

hansvm•30 minutes ago

Yeah, harness quality matters too, but the underlying model capabilities are night and day.

elahieh•about 2 hours ago

One reason might be that Claude Opus 4.7 thinking benchmarks better on Arena Coding at https://arena.ai/leaderboard/text/coding ... hopefully that effectively assesses correctness. It doesn't account for reliability though.

CompoundEyes•34 minutes ago

In my org the teams doing agent engineering at scale are all on Codex using gpt-5.5. By scale I mean fully agent authored code workflows with long running / multi hour plans.

SeanAnderson•about 1 hour ago

You get a discount for paying for a full year on Teams and Enterprise can involve contractual obligations. It's a lot of effort to get buy-in to change providers and to shift an entire organization. The winds change frequently in this space and the pain needs to get to a certain level before it's worth rolling the dice.

taspeotis•about 1 hour ago

Claude Max 20x gives me unlimited (for my level of usage) Opus 4.7 - how much money do I have pay OpenAI for that?

arcanemachiner•34 minutes ago

Based on the experience of people using the $20 Claude Pro subscription and exhausting their quotas in a manner of minutes, the answer to your question is probably "less". (I would guess that the $100 plan would do the trick.)

taspeotis•23 minutes ago

Okay so how much less will I have to pay OpenAI for unlimited Opus 4.7?

Thaxll•about 2 hours ago

I think it's impossible to say that codex x.y.z is better than Sonnet x.y.z, I used many "high" end models and they're just all good.

kylemaxwell•about 1 hour ago

Corporate policies and agreements. In large corporations, using external non-approved models with proprietary source code is a good way to have significant career issues.

etchalon•26 minutes ago

I'd rather not give money to Sam Altman.

yieldcrv•about 1 hour ago

because my shard isn’t erroring

I use Codex when Claude Code is down, and I only began using Claude when ChatGPT was down

yes codex is very fast, I go back to Claude for now

squirrellous•about 1 hour ago

Corporate reasons. AWS hasn't opened codex models to everyone yet.

echelon•about 1 hour ago

Claude is significantly better at Rust in my experience, and Rust is my favorite language to emit from LLMs.

Opus 4.7 + Rust is a killer combo.

nothinkjustai•about 2 hours ago

Because of marketing and vibes mostly.

Heck I prefer DeepSeek to both of those.

josephg•about 1 hour ago

Wow, I'm really surprised. I tried deepseek (their best model, through the official API). Its extremely cheap, but its clearly not as good at programming as Opus 4.7. It seems nowhere near as good at making high level design choices. Deepseek also seems to get stuck in whack-a-mole fixing loops much more than opus. I stopped it at one point, and asked opus to solve the problem it was trying to solve and it saw the solution immediately.

I was running deepseek through claude's code agent harness. Maybe it works better through a different tool?

zmmmmm•about 1 hour ago

I've given V4 Pro some curly things and I was impressed at how it figured them out. I agree high level design is not its forte. But it sat in a loop and dogmatically debugged a crazy dependency issue to come to the right answer over the course of 15 minutes which impressed me.

esafak•about 1 hour ago

You tried v4?

zmmmmm•about 1 hour ago

interestingly I had the same experience, and weirdly it's in part because it is clearly less intelligent. It's more of a mechanistic tool just doing what I ask (but still very smart and very competent about it) and less trying to win a nobel prize with each answer. Turns out I actually like that.

textlapse•19 minutes ago

Say what you will about Sam Altman, but at least he engages with his user base and acts on user feedback.

Dario and co seem to be on some elevated pedestal - us mere mortals are beneath them - and they have this scattershot devrel where each engineer has their own X way of communicating to the public often at odds with each other.

I loved Sonnet and Opus fwiw but not anymore.

SilverElfin•15 minutes ago

Plus I can’t really trust someone who emphasizes ethics and then partners with Elon to buy compute from a potentially illegal natural gas powered datacenter.

gopalv•about 2 hours ago

Sonnet is also throwing overloaded error.

My systems are hitting exponential delay retries, so this might not get better because retries overload things again.

> {'type': 'error', 'error': {'details': None, 'type': 'overloaded_error', 'message': 'Overloaded'}, 'request_id': 'req_ ...

I can see a weird spike in my cache hit-rate a few minutes before, so this might actually be some extra caching they have thrown in.

keithnz•about 2 hours ago

https://status.claude.com/

kristianc•about 2 hours ago

They're having quite the day for devrel..

9cb14c1ec0•about 2 hours ago

Do they need a waiting list, or what?

sinak•about 2 hours ago

Sonnet is giving an overloaded message as well.

cyanydeez•about 2 hours ago

so, all those CEOs moving all those remaining engineers to be dependent on a cloud service to the extent that there's no local development capability are gonna appologize right

claaams•about 1 hour ago

in a year or two when AI tool costs go from 5M per year to 15M per year...even then, maybe not.

FergusArgyll•about 1 hour ago

I thought the deal with xai was supposed to solve this? Is this basically the adding lanes paradox?

josephg•about 1 hour ago

You're assuming the elevated error rates are due to the system being overloaded. We have no evidence this is actually the case. Its much more likely due to a simple misconfiguration or failing router or something.

imperio59•39 minutes ago

I love Claude but I hate waiting a minute or two for any inference to start. I hope they can get their xAI capacity online ASAP and that it helps!