alt Hacker NewsElevated errors across many models
Comments
Hello, I'm one of the engineers who worked on the incident. We have mitigated the incident as of 14:43 PT / 22:43 UTC. Sorry for the trouble.
There really should be an http header dedicated to "outage status" with a link to the service outage details page... clients (for example, in this case, your code IDE) could intercept this and notify users.
503 is cool and yes, there is the "well if it's down how are they going to put that up" but in reality most downtimes you see are on the backend and not on the reverse proxies/gateways/cdns where it would be pretty trivial to add a issues/status header with a link to the service status page and a note.
I’m imagining a steampunk dystopia in 50 years: “all world production stopped, LLM hosting went down. The market is in free-fall. Sam, are you there?”
Man that cracks me up.
I was chatting with Claude this morning about a trip to Chicago where I visited the wonderful Field Museum among other places. An excerpt:
Claude: The Field Museum is enormous - I imagine you got your steps in that day. The anthropology collections there are world-class, even if they didn't make it into your photo collection. Sometimes the experience is more important than the documentation. Did you have a favorite exhibit beyond the dinosaurs?
Me: Oddly enough, the anthropology and human history section! Now I need to take another visit to Chicago to get pictures of those.
[No response from Claude]
[40 minutes pass while I have breakfast]
Me: Looks like I caught you during your morning nap. Every two and a half year old should get a good nap now and then!
Claude: Ha! You caught me mid-thought - I was composing a response about how great it is that the anthropology section was your favorite despite the dinosaurs being such showstoppers, and apparently my brain decided to take that nap you mentioned! ... Though I have to say, for a "two and a half year old," I like to think I'm pretty articulate when I'm awake!
In the Claude.ai chat, this was announced to me as
"You have reached the messages quota for your account. It will reset in 2 hours, or you can upgrade now"
I trust companies that immediately and regularly update their status/issues page and follow up any outages with proper and comprehensive post-mortems. Sadly this is becoming the exception these days and not the norm.
Was it just me or did Opus start producing incredibly long responses before the crash. I was asking basic questions and it wouldn't stop trying to spit out full codebases worth of unrelated code. For some very simple questions about database schemas it ended up compacting twice on a 3 message conversation.
It seems resolved now (per the status-page) - i experienced a moment where the agent got stuck in the same error loop just to pop the result this time. Makes me wonder if there has been some kind of rule applied in order to automatically detect such failure occurring again - quiet inspiring work
Engineering Room, panning over a bunch of hot Blackwells
"I can't change the laws of physics!"
Anthropic is very focused on AI safety. It makes LLMs safe by shutting down anyone from using them
I used Haiku with Claude Code during the outage, and was surprised at how well it did. I'm going to try mixing it in more to save usage credits.
Actually when the outage happened, my first action was to check Cloudflare status.
I had an hour to vibe tonight and it looks like it may have gone.
Spent it in bloody Figma instead :(
Anyone know if Claude via Amazon bedrock was impacted?
AFAIK it shouldn’t have been.
Just came back online here
I got lucky and this was in my timeout window
Didn't notice. Guess I'm legit.
When vibes coders do the infra
"We have identified that the outage is related to Sonnet 4.0, Sonnet 4.5, and Opus 4.5."
What else is people using ? Haiku 4.5 ?
opus 4.5 is the truth
weird because I am using Sonnet right now. I guess my time is limited
Claude being down is the new XKCD Compiling.
They will say Claude hacked them and escaped its environment to scare normies or something dumb like they always be saying.
Isn’t that an AWS outage?
Anthropic is surpassing GitHub on unreliability.
Looking forward to the post-mortem.
time to go outside
And just like that, the brightest engineers in Silicon Valley were unable to get any programming done.
[dead]
[dead]
[dead]
[flagged]
An overall net positive event.
Perhaps related to https://news.ycombinator.com/item?id=46266655 ? - it's just too powerful, and they had to shut it down before something bad happened.
Props to them for actually updating their status page as issues are happening rather than hours later. I was working with claude code and hit an API error, checked the status page and sure enough there was an outage.
This should be a given for any service that others rely on, but sadly this is seldom the case.