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

Elevated errors on Claude.ai, API, Claude Code

claudestatus.com

Post reply on HN
Print view View original

131–140 of 241 posts

Re: Elevated errors on Claude.ai, API, Claude Code

#131

Post by the_gipsy »

andai wrote: post #124
natpalmer1776 wrote: post #120

Earlier quoted context omitted.

Remember when OpenAI wasn’t allowing new subscriptions to their ChatGPT pro plans because they were oversubscribed? Pepperidge Farms remembers.

Wouldn't that be good? I remember back in the day you could only get Gmail thru an invite, it was an awesome strategy. "Currently closed for applications" creates FOMO. They'd just need to actually get the GPUs in relatively short supply. They could do it in bursts though, right? "Now accepting applications for a short time." I'm not an internet marketer but that sounds like a win win to me. People feel special, they…

Yes, "Pepperidge farm remembers" is usually about how something used to be good.

Re: Elevated errors on Claude.ai, API, Claude Code

#132

Post by scratchyone »

jjcm wrote: post #115
walthamstow wrote: post #84

Earlier quoted context omitted.

US Pacific comes online while London is still working and they can't handle it. $380bn valuation btw.

No amount of valuation can fix global supply issues for GPUs for inference unfortunately. I suspect they're highly oversubscribed, thus the reason why we're seeing them do other things to cut down on inference cost (ie changing their default thinking length).

maybe, but the response to GPU shortages being increased error rates is the concern imo. they could implement queuing or delayed response times. it's been long enough that they've had plenty of time to implement things like this, at least on their web-ui where they have full control. instead it still just errors with no further information.

Re: Elevated errors on Claude.ai, API, Claude Code

#133

Post by ai-x »

troupo wrote: post #81

In the past few weeks: - Anthropic introduced stringent limits at peak hours. By "introduced" I mean announced it on a random dev's Xitter account - Users suddenly started burning through all of their tokens even on trivial tasks. Anthropic never truly acknowledged it, their random devs posted "we're working on it". - One of the workarounds was to somewhat quietly reduce default reasoning to medium - OpenClaw and "us…

Fundamental mis-understanding of why availability is spiky

Re: Elevated errors on Claude.ai, API, Claude Code

#135

Post by hirako2000 »

scratchyone wrote: post #132
jjcm wrote: post #115

Earlier quoted context omitted.

No amount of valuation can fix global supply issues for GPUs for inference unfortunately. I suspect they're highly oversubscribed, thus the reason why we're seeing them do other things to cut down on inference cost (ie changing their default thinking length).

maybe, but the response to GPU shortages being increased error rates is the concern imo. they could implement queuing or delayed response times. it's been long enough that they've had plenty of time to implement things like this, at least on their web-ui where they have full control. instead it still just errors with no further information.

Coding is a problem solved. Claud writes the code. I edit it. I code around it.

Engineer roles dead in 6 months.

Re: Elevated errors on Claude.ai, API, Claude Code

#136

Post by scratchyone »

jwithington wrote: post #104

I think a cheat code here is to route your requests to GCP's Vertex AI, which has stronger uptimes. Can use it as a fallback or main provider. Caveats: 1) May not be economic for those on flat-rate Anthropic subscription plans 2) I work at Google.

does google actually host anthropic models themselves?? surprised anthropic allows that, given how notoriously crazy they are about distillation or weight leaks or any hints of their models being used in the wrong way.

Re: Elevated errors on Claude.ai, API, Claude Code

#138

Post by hirako2000 »

andai wrote: post #124
natpalmer1776 wrote: post #120

Earlier quoted context omitted.

Remember when OpenAI wasn’t allowing new subscriptions to their ChatGPT pro plans because they were oversubscribed? Pepperidge Farms remembers.

Wouldn't that be good? I remember back in the day you could only get Gmail thru an invite, it was an awesome strategy. "Currently closed for applications" creates FOMO. They'd just need to actually get the GPUs in relatively short supply. They could do it in bursts though, right? "Now accepting applications for a short time." I'm not an internet marketer but that sounds like a win win to me. People feel special, they…

In the case of Gmail that was fake scarcity.

In the case of Anthropic is fake availability.

Sam Altman explained the idea is to scale the thing up, and see what happens.

He hadn't claimed to offer a solution to the supply problem that would unfold.

Re: Elevated errors on Claude.ai, API, Claude Code

#139

Post by AndroTux »

ai-x wrote: post #130
parthdesai wrote: post #11

Coding is solved

Nothing to do with coding and everything to do with capacity. In fact, this proves that there is no AI Bubble and we are massively capacity constrained (aka we under-invested in infrastructure)

I can't sign in. We're not at capacity for OAuth servers or relational databases. This proves that vibe coding your infrastructure is a bad idea.

Re: Elevated errors on Claude.ai, API, Claude Code

#140

Post by rkuska »

jakobloekke wrote: post #34

Have anyone found good techniques to get a session out of Claude Code, so that I can point another tool at it and pick up there? This always seems to happen at the worst possible time, after having spent an hour getting deep into something – half finished edits across files, subagents running, etc.

I’ve built a browser cli for that.

https://github.com/rkuska/carn

Post reply on HN