Live data from Hacker News

Elevated error rate across multiple models

status.claude.com

111–120 of 293 posts

Re: Elevated error rate across multiple models

#111

Imagine a future where Anthropic holds your company hostage because no one can code properly anymore by hand and demands paying 200% higher price for the usage. What can your company do?

the company will switch to a different LLM vendor??

what does someone do when a certain brand coffee maker keeps breaking; they buy a different brand.

Re: Elevated error rate across multiple models

#112
post #60

Incredible how we can claim productivity increases when its either Claude or Github shitting the bed every other day. It must even itself out to a net neutral gain in the long term.

I don't understand this comment. At worst, we're just back to the baseline - working without AI help.

The baseline is forever gone. Good luck convincing people to contribute to StackOverflow v2 after this.

Re: Elevated error rate across multiple models

#113
post #38
post #18

I suppose it's a good time to encourage people trying out pi[1] with any cheap model from the openrouter rankings page[1]. [1] https://pi.dev/ [2] https://openrouter.ai/rankings

"curl -fsSL https://pi.dev/install.sh | sh" — seriously? That tells me a lot about the whole project, unfortunately.

Seriously, what is the threat model here?

Re: Elevated error rate across multiple models

#115

I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. — Boris Cherny, head of Claude Code Reliability is a direct reflection of the quality of the underlying infrastructural code. If even Anthropic, the company with the world's best agentic vibecoders, has horribly unreliable infrastructure, it really says something about the quality of the world…

I wonder how they fix things when Claude is down.

This is ( or will be in the future ) a surprisingly relevant issue

Re: Elevated error rate across multiple models

#116

I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. — Boris Cherny, head of Claude Code Reliability is a direct reflection of the quality of the underlying infrastructural code. If even Anthropic, the company with the world's best agentic vibecoders, has horribly unreliable infrastructure, it really says something about the quality of the world…

I wonder how they fix things when Claude is down.

I would bet that they have inference setup for internal use on a separate system from the customer-facing production environment. The same way telemetry infrastructure needs to be run separate from normal production systems, so you aren't "blind" when you need it most.

Re: Elevated error rate across multiple models

#117

Imagine a future where Anthropic holds your company hostage because no one can code properly anymore by hand and demands paying 200% higher price for the usage. What can your company do?

No need to make up speculative futures based on a company only giving one model to their employees. I use Codex, Antigravity, Claude and GLM-5.2 interchangeably. Any sensible employer will do the same.

Re: Elevated error rate across multiple models

#118

Imagine a future where Anthropic holds your company hostage because no one can code properly anymore by hand and demands paying 200% higher price for the usage. What can your company do?

Won't it eventually be $1,000 or $5,000 a month? $5k a month would still be 97% less than many developers cost.

Re: Elevated error rate across multiple models

#119

I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. — Boris Cherny, head of Claude Code Reliability is a direct reflection of the quality of the underlying infrastructural code. If even Anthropic, the company with the world's best agentic vibecoders, has horribly unreliable infrastructure, it really says something about the quality of the world…

Meh, this is the "must be the veganism" fallacy: if someone knows you're vegan, then any ailment you might have, no matter how ubiquitous in the population, must be somehow due to your vegan diet and no more details are required.

Except now it's the "AI did it" fallacy where if you know a company uses AI, even infra scaling issues must be due to AI, and if you had just used less or no AI, you would have been spared even though that has never been true.

The usual response to this goes something like "well they made claims that AI is good" therefore anything short of perfection supposedly debunks the claim.

Re: Elevated error rate across multiple models

#120

Earlier quoted context omitted.

Yeah, totally reasonable comment given the utter security that must come from anthropic with their installer, amiright? oh wait... "curl -fsSL https://claude.ai/install.sh | bash" (right from https://claude.com/product/claude-code ) Further - what the flicking fuck do you think an installer is going to do on your system? Not run any commands? Because I've written installers for every platform... they ALL can run comm…

And you can simply look at the installer by pulling it up in the browser.

You can simply look at the installer by leaving off the "| bash".
Post reply on HN