23 comments

[ 3.1 ms ] story [ 44.8 ms ] thread
API Error: 529 Overloaded. This is a server-side issue, usually temporary — try again in a moment. If it persists, check https://status.claude.com.
I noticed it in real time, unfortunately. Perhaps the token bonfire I've been feeding all day is to blame...
Seen this yesterday as well.
Interestingly not Opus 4.5 apparently, which is still available via API.
Better buy more capacity from SpaceX.
Times like this remind me that despite GLM and Codex and other models being hyped up as Claude Opus 4.8 replacements, I still would not trust them with my most important work. For example, right now I'm working on a huge refactoring project, and even Opus has struggled with it after several days. I cannot even imagine how GLM, Codex, or other models would handle this. So the only option for me is to wait until this outage is over.

And it's not like open models are cheap to run even as alternatives. For example, with my $100/mo subscription for Claude Code, I often burn more than $100 a day several times a week. But if I were to use the API of GLM, it would be about $300.

It has been like that all of last week
529s as a forcing function for taking a walk
They have been screwing around in the back-end, for a while. They are doing something and not being transparent, re-routing the models, degrading performance and intelligence and all week post-fable ban the quality was garbage, last day and a half it improved, last half an hour degraded, now it's down.
dang et al,

"Service X is down" is not "news". Kinda feels like points-farming.

Anyone caring that X works is gonna know it's down - they can't work! And probably why they are at HN ;)

HN as an "is service X down?" detector is less reliable than trying the actual service :)

If HN is gonna keep letting people post "X is down" no worries. But it seems worth a flag.

Per their status page, the main product now has one 9 of uptime.
This happens all the time. Nothing to see here
My speculation is that we'll get fable back tomorrow. Usually we see messy devops stuff or maybe nerfing(not much these days) around the time they're releasing new models
I have two sessions going. It’s my fault. Sorry guys.
This mess sounds like a begining to skynet:)
Lots of downtime on CC the last few days. They also pushed an bad release to CC that kept doing 'No response from API · Retrying in .... check your network'. 'claude install stable' fixed that. How I was not on stable I have no idea. I can only guess how many tokens I was billed for sending requests that CC got 'No response from API' for. I have a feeling the big AI vendors won't have the loyalty that IDEs and other dev tools generate. They really need to work on trust now to avoid people hopping later.
(comment deleted)
Opus 4.8 is nearly unusable at the moment. Making extremely obvious errors, failing to debug issues even after being prompted with the exact line of code where the problem is. It should be illegal not to disclose serious degradations of performance while still charging full price. It may just be my region's datacentres degraded or something. The company is so opaque about what's happening, it's impossible to know what is actually going on.

The optimistic take is they're preparing to relaunch Fable 5 in the next day or so and siphoning off power for that. Perhaps they're doing a snap retraining to strip out any cybersecurity capability.