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

Claude.ai unavailable and elevated errors on the API

status.claude.com

Post reply on HN
Print view View original

181–190 of 277 posts

Re: Claude.ai unavailable and elevated errors on the API

#181

Post by GenerWork »

johndough wrote: post #159
justrunitlocal wrote: post #89

We've been running our 10 dev org on 8 H100s on open models (with some tweaks). Sure they aren't as good as the big providers but they 1. don't go down 2. have pretty damn high tok/s. It pays for itself. Posting with a fresh account because I'm not supposed to share these details for obvious reason. If you want help on setting this up, just reply with a way to reach you.

> Sure they aren't as good as the big providers If you haven't done so already, finetune the model on all your company's code that you can get your hands on. This is one of the great advantages that you get when running local models. I like the style of the generated code much better now, I have to rewrite much less, and my prompts can be shorter too. But maybe these already are the "tweaks" that you mentioned.

How would they do that? Would it be as easy as telling a model "Hey, review all this code, identify patterns, and then write in this style going forward"?

Sorry if this is a stupid question, I've never finetuned or trained a LLM.

Re: Claude.ai unavailable and elevated errors on the API

#182

Post by JamesSwift »

thepasch wrote: post #175
JamesSwift wrote: post #165

Earlier quoted context omitted.

How do things like prompt caching etc play into that? Would I theoretically have a more stable harness backing my usage? Im seriously over the current claude experience. After seemingly fixing my 4.6 usage by disabling adaptive thinking and moving to max effort, it seems that the release of 4.7 has broken that workflow and Im 99% certain that disabling adaptive thinking does nothing even on 4.6 now. Just egregious er…

> Would I theoretically have a more stable harness backing my usage? If you don’t mind an opinionated harness that asks for a pretty specific workflow, but one that works well, use OpenCode. If you want to spread your wings and feel the sweet kiss of freedom, use Pi.

Im looking at moving to Pi and I like the minimal nature, but I disagree with a handful of decisions they make. So Id likely need to maintain a fork which is less than ideal.

Re: Claude.ai unavailable and elevated errors on the API

#183

Post by zackify »

thepasch wrote: post #175
JamesSwift wrote: post #165

Earlier quoted context omitted.

How do things like prompt caching etc play into that? Would I theoretically have a more stable harness backing my usage? Im seriously over the current claude experience. After seemingly fixing my 4.6 usage by disabling adaptive thinking and moving to max effort, it seems that the release of 4.7 has broken that workflow and Im 99% certain that disabling adaptive thinking does nothing even on 4.6 now. Just egregious er…

> Would I theoretically have a more stable harness backing my usage? If you don’t mind an opinionated harness that asks for a pretty specific workflow, but one that works well, use OpenCode. If you want to spread your wings and feel the sweet kiss of freedom, use Pi.

pi for the win, i have my own ai extend it when i want more specific features. vibe coded in 20 minutes shift+tab like claude code to add permission control.

Re: Claude.ai unavailable and elevated errors on the API

#185

Post by SimianSci »

2ndorderthought wrote: post #174
SimianSci wrote: post #98

Earlier quoted context omitted.

we are in the SMB space, the spend is almost entirely usage for us at this point, rather than seat cost. For context, we are a software firm focused on difficult engineering problems, but I cant divulge much else.

Have you guys considered running your own local models? 200k a month is a ton of money and puts all your eggs in one basket. Or is it easier to just be able to run away from it all if you are done with it or something changes?

I led the team that did the math and analysis for determining our direction in selecting Anthropic. We initially assumed this was where we would end up, but after some investment exploring our options we found it not worth the trouble.

Local models sound great until you realize you dont get alot of the features that we implicitly expect from hosted models. Many things would require additional investment into the operations and setup to get to a comparable system. We ended up wanting things that would require us to roll our own memory system, harnesses for the model, compliance needs, and security. It was possible for us to invest in this, but it would require additional investment in hiring or training to get us to a state comparable to the hosted options.

Eventually, I had to recommend against the project as it was more likely to be an investment in the leading team's resume, than an actual investment into our organization.

Re: Claude.ai unavailable and elevated errors on the API

#186

Post by kinematikk »

jtfrench wrote: post #54

If this can happen to Anthropic, imagine all the companies building on top of Claude Code for live products. Hopefully the industry is learning that competent problem solving human engineers are still very much needed when you have increasingly deceptive non-deterministic genies running your production stack.

Sadly its "good enough" for execs

Re: Claude.ai unavailable and elevated errors on the API

#187

Post by subscribed »

samuelknight wrote: post #134
jtfrench wrote: post #54

If this can happen to Anthropic, imagine all the companies building on top of Claude Code for live products. Hopefully the industry is learning that competent problem solving human engineers are still very much needed when you have increasingly deceptive non-deterministic genies running your production stack.

It's not that simple. API is still up and there are multiple API providers. https://openrouter.ai/anthropic/claude-opus-4.7

I don't think there are many other companies serving Claude.

Re: Claude.ai unavailable and elevated errors on the API

#188

Post by sva_ »

Hamuko wrote: post #173
lousken wrote: post #133

Earlier quoted context omitted.

Can't they use Mythos to figure out their uptime?

They weren't able to use it to prevent Claude Code source code from leaking, or from some random Discord server from gaining access to Mythos.

> prevent Claude Code source code from leaking

That's silly. It's a JavaScript app, they are more or less open source by design. There was no secret sauce in Claude Code.

Re: Claude.ai unavailable and elevated errors on the API

#189

Post by esafak »

wg0 wrote: post #138
SimianSci wrote: post #41

The spend at my organization has reached beyond the $200,000 per month level on Anthropic's enterprise tier. The amount of outages we have had over these past few months are astounding and coupled with their horrendous support it has our executive team furious. its alot of money to be spending for a single 9 of reliablility.

Speaking of developer tooling spend - IDEs are far harder to build such as JetBrain etc and don't think any IDE would be charging this amount to any customer per month. Not sure how much of a productivity gain a 2.5 million per year it is?

IDEs don't need expensive GPUs to create and serve.

Re: Claude.ai unavailable and elevated errors on the API

#190

Post by mrguyorama »

Cider9986 wrote: post #37

How are they going to fix it if the AI that designed it isn't working?

Large telcos often have a chunk of subscriptions with their biggest competitor so that when they absolutely explode and everything is down, they can still communicate to bring it back up.

Clearly, half of Anthropic should have subscriptions to OpenAI or Mistral or whatever China sells.

Post reply on HN