A nice chance to try sonnet again, must say, I'm not missing the load bearing assumptions, honest read of the permission matrix, what's genuinely a Django convention and what's a design choice, what's worth my thinking, and what's worth being precise about.
Long story short, it seems to be faster and less vocal but not much dumber (it's just my thinking partner, so I read a lot of the output as I create a large data model).
I've almost entirely stopped using Opus 5, at least with Sonnet I know what i'm getting -- Fable for the complex stuff and Sonnet for the precision changes.
The verbosity of Opus 5 isn't even my issue, it's consistency. For every 10 tasks Opus 5 accomplishes, there's at least one task that Opus 5 does just an atrocious job of, or a debugging investigation that it just completely goes off the rails on.
My engineering has changed so much that I'm now using this time to catch up on emails and think about design and architecture for the next leg of work. (And post on HN, of course.)
I would never have predicted this a year ago.
I always scoffed about engineers not doing work during Github outages - I'd always find some kind of other engineering to do if PRs or builds were piling up.
But during model outages, and since I'm not actively set up to use OpenAI/Codex at the moment, I'll just find something else productive to do. I don't think I'm ever going to write code by hand again unless I'm fixing something the AI can't manage or the change is small enough. Why even try when the machine is 100x faster?
Should I give Codex another try? It's been a month or so since I last used it, and it always felt inferior at Rust and TypeScript.
For over a decade we've had to deal with github downtime posts where HNers race to be the first person to point out how they understand that git is decentralized.
Now we have to deal with AI service downtime posts forever where HNers race to be the guy who has switched to some other provider and whatever snark it's gonna come with.
The interesting thing is they changed default mode for Claude code to auto mode and auto mode uses sonnet to decide whether the command is safe or not. With their Sonnet model outage, the entire thing stopped working.
here is the error it was throwing:
> Error: claude-sonnet-5[1m] is temporarily unavailable (overloaded), so auto mode cannot determine the safety of Edit right now. Wait a moment and then try this action again. If it keeps failing, continue with other tasks that don't require this action and come back to it later. Note: reading files, searching code, and other read-only operations do not require the classifier and can still be used.
Demand > supply. It's impressive that customers have not migrated en masse to other providers, given the frequency of these outages. Perhaps switching costs are greater than some would believe. Or, qualitative differences between models continue to exist, despite matching on public benchmarks.
I did migrate 80% of my tokens. But for some tasks claude models are still the best.
Easy workaround is to work outside US peak hours (europe morning). I love this outages, I am hardly affected, and weekly reset usually promptly follows!
>> Perhaps switching costs are greater than some would believe.
I haven't switched because there's nothing to switch to that is anywhere as good. I've been making dedicated attempts at using Sol but it falls short, despite what some people claim.
That's quite a reach. More likely someone merged and deployed their vibe-coded PR and is now figuring out how to bring the service back up.
If there's a lot of demand for rollercoaster rides, the rollercoaster will not stop operating; instead the queue of people in front of it will increase.
It's not like a bridge or elevator where we have a certain number of people that can use it, and if one more person joins, the whole structure breaks apart and everybody perishes.
Those guys are running a website that provides an interface for some specific hardware. Just like file hosting providers back in the day selling their terabyte-sized hard disks in 100MB-increments.
> instead the queue of people in front of it will increase.
This can ultimately result in the system breaking. I don't think Anthropic engineers are that much worse than their peers, such that they are 10x more prone to causing outages due to bad deployments.
Do you really think it’s a coincidence claude outages always happen when US and EU workdays overlap?
Anthropic is a trillion dollar company and employs way more skilled high-paid engineers than you are btw, you really think it’s a systems issue not capacity
Setting aside annoyance at the downtime, I'm really curious about the reasons for the failures, because I have to imagine there are some novel failure modes when serving these giant models that I haven't experienced with the kind of work I've done.
Anyone out there working in this space who can elucidate us on interesting failure scenarios unique to the space?
If I didn't know any better, I would have said Grok is using Claude behind the hood. But definitely curious now why it’s happening with both these LLM providers around the same time
Kind of cool how fable 5.1 just worked around these by reassigning subagents to non-failing models with more supervision and now with a hint to Sol and Flash 3.8.
I just experienced this through OpenRouter and filed a refund request. I'm curious how OpenRouter handles incidents like this across such a large number of models and providers.
Officially signing up for the $200 Codex plan now. I do like CC, but these errors are happening every week now, and if they (Anthropic) gave regular resets that's one thing, but somehow I'm already at 62% weekly usage after the random reset this Tuesday using Fable 5.1 medium. Just not worth it any longer compared to Codex IMO. I already set up my skills and everything to be generic and not CC specific, so it shouldn't be too hard to transition over. I'll run both for a month and decide.
Haha, I was more like: I have to think alone now. But I get the feeling, as someone who has always made a point of using only foss on my own machines (own the means of production so to say), this is a weird time. I don't like it, I hope soon local models get good. But in the mean time... We have this... dependency.
I use a lot of spec driven development today. It does allow me to make workflows that were on my Life's backlog for months or years in 10~20 minutes. It's amazing, but also I lack ownership over the thing made. It's like I paid a contractor.
I can feel that my actual cognitive engineering skills are in decline. Does anyone else see this? To those of you who haven't hand written a PR in months, can you still write your own personal software as easily as you once could?
Cost and reliability are the two reasons why we don't use Claude in our product. Getting close to one nine, that's not something one can build a reliable product upon. We now use OpenAI with Gemini fallback (or vice versa depending on use case).
Personally I like Claude and have the 20x Max plan but even there I burned through the whole weekly quota with 3 prompts in less than a day using the new Fable 5.1 which is crazy. Now Opus 5 is down. These two issues are really testing my patience.
Every time I see Anthropic ship an issue like this, I'm reminded of Boris Cherny's glorious quote: "At this point it's safe to say that coding is largely solved."
During each forced workflow interruption I look for alternatives. No matter if I can't use the product due to a server outage or due to their weird quota limitations.
This can't be good for retention numbers. Old-school VCs would've ripped them apart in the air. Where did all the expertise go?
I suspect the only reason those alternative providers have better up-time and more generous quotas, is because they don't have nearly the same amount of demand. Notice that Deepseek recently had to increase their pricing, once it gained it popularity.
Long story short, it seems to be faster and less vocal but not much dumber (it's just my thinking partner, so I read a lot of the output as I create a large data model).
Good for more precise changes.
The verbosity of Opus 5 isn't even my issue, it's consistency. For every 10 tasks Opus 5 accomplishes, there's at least one task that Opus 5 does just an atrocious job of, or a debugging investigation that it just completely goes off the rails on.
I would never have predicted this a year ago.
I always scoffed about engineers not doing work during Github outages - I'd always find some kind of other engineering to do if PRs or builds were piling up.
But during model outages, and since I'm not actively set up to use OpenAI/Codex at the moment, I'll just find something else productive to do. I don't think I'm ever going to write code by hand again unless I'm fixing something the AI can't manage or the change is small enough. Why even try when the machine is 100x faster?
Should I give Codex another try? It's been a month or so since I last used it, and it always felt inferior at Rust and TypeScript.
Now we have to deal with AI service downtime posts forever where HNers race to be the guy who has switched to some other provider and whatever snark it's gonna come with.
Looks like trouble in the SpaceX datacenters.
here is the error it was throwing:
> Error: claude-sonnet-5[1m] is temporarily unavailable (overloaded), so auto mode cannot determine the safety of Edit right now. Wait a moment and then try this action again. If it keeps failing, continue with other tasks that don't require this action and come back to it later. Note: reading files, searching code, and other read-only operations do not require the classifier and can still be used.
Easy workaround is to work outside US peak hours (europe morning). I love this outages, I am hardly affected, and weekly reset usually promptly follows!
I haven't switched because there's nothing to switch to that is anywhere as good. I've been making dedicated attempts at using Sol but it falls short, despite what some people claim.
If there's a lot of demand for rollercoaster rides, the rollercoaster will not stop operating; instead the queue of people in front of it will increase.
It's not like a bridge or elevator where we have a certain number of people that can use it, and if one more person joins, the whole structure breaks apart and everybody perishes.
Those guys are running a website that provides an interface for some specific hardware. Just like file hosting providers back in the day selling their terabyte-sized hard disks in 100MB-increments.
This can ultimately result in the system breaking. I don't think Anthropic engineers are that much worse than their peers, such that they are 10x more prone to causing outages due to bad deployments.
Anthropic is a trillion dollar company and employs way more skilled high-paid engineers than you are btw, you really think it’s a systems issue not capacity
Anyone out there working in this space who can elucidate us on interesting failure scenarios unique to the space?
If I didn't know any better, I would have said Grok is using Claude behind the hood. But definitely curious now why it’s happening with both these LLM providers around the same time
I can feel that my actual cognitive engineering skills are in decline. Does anyone else see this? To those of you who haven't hand written a PR in months, can you still write your own personal software as easily as you once could?
lol
Anthropic, please hire a literate human.
This can't be good for retention numbers. Old-school VCs would've ripped them apart in the air. Where did all the expertise go?