Elevated Errors Across Many Models
Posted20 days agoActive16 days ago
status.claude.comTech DiscussionstoryHigh profile
informativeneutral
Debate
0/100
AnthropicOutageLarge Language Models
Key topics
Anthropic
Outage
Large Language Models
Discussion Activity
Very active discussionFirst comment
2m
Peak period
145
0-6h
Avg / period
20
Comment distribution160 data points
Loading chart...
Based on 160 loaded comments
Key moments
- 01Story posted
Dec 14, 2025 at 4:53 PM EST
20 days ago
Step 01 - 02First comment
Dec 14, 2025 at 4:55 PM EST
2m after posting
Step 02 - 03Peak activity
145 comments in 0-6h
Hottest window of the conversation
Step 03 - 04Latest activity
Dec 18, 2025 at 9:47 AM EST
16 days ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 46267385Type: storyLast synced: 12/17/2025, 9:45:42 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
What else is people using ? Haiku 4.5 ?
So we can maybe vibe, depending what service we use.
They made pro have many times more value than paying per token and then they made max again have 25x more tokens than pro on the $200 plan.
It’s a bit like being offered a tiny bag of rice for $20 or a cargo ships worth for $200. That’s the pricing structure right now.
So while i agree you can’t easily exceed the quota on the big plans it’s a little crazy how they’ve tiered pricing. I hope no one out there’s paying per token!
Some companies are. Yes, for Claude Code. My co used to be like that as it's an easy ramp up instead of giving devs who might not use it that much a $150/mo seat; if you use it enough you can have a seat and save money, but if you're not touching $150 in credits a month just use the API. Oxide also recommends using API pricing. [0]
0: https://gist.github.com/david-crespo/5c5eaf36a2d20be8a3013ba...
For comparison’s sake, this is clear: https://support.cerebras.net/articles/9996007307-cerebras-co...
And while the Cerebras service is pretty okay, their website otherwise kinda sucks - and yet you can find clear info!
Man that cracks me up.
But what about when LLMs go down and a good chunk of a whole generation won't even know how to think, when the remote system goes down? (Is the ability to think "the engine" of self and agency in this metaphor?)
We are building a wildly irresponsible context to exist in.
There is a very interesting thing happening right now where the "llm over promisers" are incentivized to over promise for all the normal reasons -- but ALSO to create the perception that the "next/soon" breakthrough is only going to be applicable when run on huge cloud infra such that running locally is never going to be all that useful ... I tend to think that will prove wildly wrong and that we will very soon arrive at a world where state of art LLM workloads should be expected to be massively more efficiently runnable than they currently are -- to the point of not even being the bottleneck of the workflows that use these components. Additionally these workloads will be viable to run locally on common current_year consumer level hardware ...
"llm is about to be general intelligence and sufficient llm can never run locally" is a highly highly temporary state that should soon be falsifiable imo. I don't think the llm part of the "ai computation" will be the perf bottleneck for long.
I've often thought that local power generation (via solar or wind) could be (or could have been) a viable alternative to national grid supply.
For coding, creativity is not necessarily a good thing. There are well established patterns, algorithms, and applications could reasonably be construed as "good enough" to assist with the coding itself. Adding a human language model over that to understand the user's intents could be considered an overlay on the coding model.
I confess that this is willful projection of my hope to be able to self-host agents on affordable hardware. A frontier model on powerful hardware would always be preferable but sometimes "good enough" is just that.
I wouldn't pay for it for myself but I can see employers considering it.
Imagination, either the first or last thing to die in 2075.
Is it so different?
“So sorry, we can’t read the WiFi signal from your generator. We don’t know how much to tax you for the emissions. Sadly, we can’t allow it to start.”
The story writes itself.
Crazy: https://www.youtube.com/shorts/SV4DMqAJ8RQ
This should be a given for any service that others rely on, but sadly this is seldom the case.
Claude user base believes in Sunday PM work sessions
I was also fortunate to be using Claude at that exact moment (for personal reasons), which meant I could immediately see the severity of the outage.
https://www.theguardian.com/technology/2021/oct/05/facebook-...
I have a memory that Slack fell into this trap too (I could be wrong)
Google SRE still keeps IRC available in case of an emergency.
Today seems like things finally hit a tipping point.
Of course, they may not have been aware of the previous instability. But that would be concerning in a different way.
Only curious as a developer and dev op. It's all quite interesting where and how things go wrong especially with large deployments like Anthropic.
https://youtu.be/uRGljemfwUE?si=Sq0t-2ipXr_gDqao&t=69
The bad route has been removed and service is restored. We’re doing a full review internally with a focus on synthetic monitoring and better visibility into high-impact infrastructure changes to catch these faster in the future.
Back when I did website QA Automation I'd manually check the website at the end of my day. Nothing extensive, just looking at the homepage for piece of mind.
Once a senior engineer decided to bypass all of our QA, deploy and took down prod. Fun times.
At my first job one of my more senior team members would throw caution to the wind and deploy at 3pm or later on Fridays because he believed in shipping ASAP.
There were a couple times that those changes caused weekend incidents.
Did the bad route cause an overload? Was there a code error on that route that wasn’t spotted? Was it a code issue or an instance that broke?
Network routes consist of a network (a range of IPs) and a next hop to send traffic for that range to.
These can overlap. Sometimes that’s desirable, sometimes it is not. When routers have two routes that are exactly the same they often load balance (in some fairly dumb, stateless fashion) between possible next hops, when one of the routes is more specific, it wins.
Routes get injected by routers saying “I am responsible for this range” and setting themselves as the next hop, others routers that connect to them receive this advertisement and propagate it to their own router peers further downstream.
An example would be advertising 192.168.0.0/23, which is the range of 192.168.0.0-192.168.1.255.
Let’s say that’s your inference backend in some rows in a data center.
Then, through some misconfiguration, some other router starts announcing 192.168.1.0/24 (192.168.1.0-192.168.1.255). This is more specific, that traffic gets sent there, and half of the original inference pod is now unreachable.
Underneath a public statement they all have extremely detailed post-mortems. But how much goes public is 100% random from the customer's perspective. There's no Monday Morning QB'ing the CEO, but there absolutely is "Day-Shift SRE Leader Phil"
A tech company that publishes the postmortems when possible always get a +1 in my eyes, I think it's a sign of good company culture. Cloudflare's are great and I would love to see more from others in the industry.
I don’t even bother with Sonnet anymore, it’s been made obsolete by Opus 4.5.
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.
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!
Spent it in bloody Figma instead :(
1. https://news.ycombinator.com/item?id=46223311 (Gemini frustrating) 2. https://news.ycombinator.com/item?id=46063531 (Ilya same as Yann Lecun) 3. Opus does not make it to front page and gets flagged: https://news.ycombinator.com/item?id=46266655 4. This thing making to front page
we let you run compute across any cloud so if a region/cloud experiences an issue, users are served on surviving regions/clouds/on-prem.
Cheers, Doron
AFAIK it shouldn’t have been.
"I can't change the laws of physics!"
Looking forward to the post-mortem.